< Prev | Home | Model | Random | Next >

Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 3050 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')



Text #0

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2405. Min Act: -0.0001

Data Index: 1779540 (The Pile)

Max Activating Token Index: 1005

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2862. Min Act: -0.0001

Data Index: 476674 (The Pile)

Max Activating Token Index: 114

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2449. Min Act: -0.0001

Data Index: 1698518 (The Pile)

Max Activating Token Index: 146

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2698. Min Act: -0.0001

Data Index: 1465638 (The Pile)

Max Activating Token Index: 158

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2412. Min Act: -0.0001

Data Index: 1488450 (The Pile)

Max Activating Token Index: 47

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2315. Min Act: -0.0001

Data Index: 812963 (The Pile)

Max Activating Token Index: 950

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2384. Min Act: -0.0001

Data Index: 1325870 (The Pile)

Max Activating Token Index: 69

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2780. Min Act: -0.0001

Data Index: 602873 (The Pile)

Max Activating Token Index: 72

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2452. Min Act: -0.0001

Data Index: 775801 (The Pile)

Max Activating Token Index: 48

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2420. Min Act: -0.0001

Data Index: 1834609 (The Pile)

Max Activating Token Index: 50

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2653. Min Act: -0.0001

Data Index: 1360816 (The Pile)

Max Activating Token Index: 64

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2264. Min Act: -0.0001

Data Index: 157143 (The Pile)

Max Activating Token Index: 881

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2212. Min Act: -0.0001

Data Index: 223128 (The Pile)

Max Activating Token Index: 58

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2439. Min Act: -0.0001

Data Index: 1052264 (The Pile)

Max Activating Token Index: 76

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2392. Min Act: -0.0001

Data Index: 210155 (The Pile)

Max Activating Token Index: 686

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2230. Min Act: -0.0001

Data Index: 133702 (The Pile)

Max Activating Token Index: 943

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2187. Min Act: -0.0001

Data Index: 634254 (The Pile)

Max Activating Token Index: 71

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2153. Min Act: -0.0001

Data Index: 418544 (The Pile)

Max Activating Token Index: 27

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2494. Min Act: -0.0001

Data Index: 1161978 (The Pile)

Max Activating Token Index: 64

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2307. Min Act: -0.0001

Data Index: 1428188 (The Pile)

Max Activating Token Index: 49

Click toggle to see full text

Truncated

Full Text #19