< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 11 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.3536. Min Act: -0.0001

Data Index: 200887 (The Pile)

Max Activating Token Index: 12

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.3646. Min Act: -0.0001

Data Index: 436081 (The Pile)

Max Activating Token Index: 442

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2961. Min Act: -0.0001

Data Index: 727258 (The Pile)

Max Activating Token Index: 642

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.3283. Min Act: -0.0001

Data Index: 1751254 (The Pile)

Max Activating Token Index: 14

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2905. Min Act: -0.0001

Data Index: 890984 (The Pile)

Max Activating Token Index: 392

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2999. Min Act: -0.0001

Data Index: 1427512 (The Pile)

Max Activating Token Index: 150

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2790. Min Act: -0.0001

Data Index: 1216655 (The Pile)

Max Activating Token Index: 748

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2956. Min Act: -0.0001

Data Index: 154595 (The Pile)

Max Activating Token Index: 273

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.3155. Min Act: -0.0001

Data Index: 1839326 (The Pile)

Max Activating Token Index: 284

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2584. Min Act: -0.0001

Data Index: 1483679 (The Pile)

Max Activating Token Index: 128

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2949. Min Act: -0.0001

Data Index: 1132520 (The Pile)

Max Activating Token Index: 356

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2686. Min Act: -0.0001

Data Index: 1538781 (The Pile)

Max Activating Token Index: 137

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2615. Min Act: -0.0001

Data Index: 1985897 (The Pile)

Max Activating Token Index: 742

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2769. Min Act: -0.0001

Data Index: 88333 (The Pile)

Max Activating Token Index: 408

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2808. Min Act: -0.0001

Data Index: 815348 (The Pile)

Max Activating Token Index: 458

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2947. Min Act: -0.0001

Data Index: 831280 (The Pile)

Max Activating Token Index: 1001

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.3033. Min Act: -0.0001

Data Index: 1456198 (The Pile)

Max Activating Token Index: 47

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2811. Min Act: -0.0001

Data Index: 601436 (The Pile)

Max Activating Token Index: 45

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2794. Min Act: -0.0001

Data Index: 983384 (The Pile)

Max Activating Token Index: 155

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2881. Min Act: -0.0001

Data Index: 1573558 (The Pile)

Max Activating Token Index: 644

Click toggle to see full text

Truncated

Full Text #19