< Prev | Home | Model | Random | Next >

Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 26 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')



Text #0

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.3008. Min Act: -0.0001

Data Index: 1494314 (The Pile)

Max Activating Token Index: 691

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.3225. Min Act: -0.0001

Data Index: 1804678 (The Pile)

Max Activating Token Index: 766

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.3046. Min Act: -0.0001

Data Index: 669381 (The Pile)

Max Activating Token Index: 210

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.2670. Min Act: -0.0001

Data Index: 1238435 (The Pile)

Max Activating Token Index: 693

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.2939. Min Act: -0.0001

Data Index: 500308 (The Pile)

Max Activating Token Index: 756

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.2792. Min Act: -0.0001

Data Index: 78259 (The Pile)

Max Activating Token Index: 972

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.2795. Min Act: -0.0001

Data Index: 1716836 (The Pile)

Max Activating Token Index: 268

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.2772. Min Act: -0.0001

Data Index: 1146956 (The Pile)

Max Activating Token Index: 213

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.2872. Min Act: -0.0001

Data Index: 1927021 (The Pile)

Max Activating Token Index: 1000

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.2600. Min Act: -0.0001

Data Index: 494973 (The Pile)

Max Activating Token Index: 973

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.2644. Min Act: -0.0001

Data Index: 1693245 (The Pile)

Max Activating Token Index: 208

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.2455. Min Act: -0.0001

Data Index: 1649301 (The Pile)

Max Activating Token Index: 827

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.2630. Min Act: -0.0001

Data Index: 415642 (The Pile)

Max Activating Token Index: 623

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.2814. Min Act: -0.0001

Data Index: 1205966 (The Pile)

Max Activating Token Index: 503

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.2661. Min Act: -0.0001

Data Index: 1237640 (The Pile)

Max Activating Token Index: 882

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.2628. Min Act: -0.0001

Data Index: 1645478 (The Pile)

Max Activating Token Index: 684

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.2510. Min Act: -0.0001

Data Index: 577110 (The Pile)

Max Activating Token Index: 958

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.2728. Min Act: -0.0001

Data Index: 259031 (The Pile)

Max Activating Token Index: 684

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.2678. Min Act: -0.0001

Data Index: 705061 (The Pile)

Max Activating Token Index: 5

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.2694. Min Act: -0.0001

Data Index: 778922 (The Pile)

Max Activating Token Index: 253

Click toggle to see full text

Truncated

Full Text #19