Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 1142 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.6048. Min Act: -0.0000

Data Index: 1989521 (The Pile)

Max Activating Token Index: 124

Text #1

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.4626. Min Act: -0.0000

Data Index: 209398 (The Pile)

Max Activating Token Index: 33

Text #2

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.4365. Min Act: 0.0000

Data Index: 112768 (The Pile)

Max Activating Token Index: 1019

Text #3

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.4058. Min Act: -0.0000

Data Index: 591848 (The Pile)

Max Activating Token Index: 763

Text #4

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.3692. Min Act: -0.0000

Data Index: 1833419 (The Pile)

Max Activating Token Index: 810

Text #5

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.3918. Min Act: -0.0000

Data Index: 1643191 (The Pile)

Max Activating Token Index: 977

Text #6

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.3729. Min Act: 0.0000

Data Index: 340642 (The Pile)

Max Activating Token Index: 658

Text #7

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.3787. Min Act: -0.0000

Data Index: 512494 (The Pile)

Max Activating Token Index: 269

Text #8

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.3660. Min Act: 0.0000

Data Index: 979685 (The Pile)

Max Activating Token Index: 167

Text #9

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.3577. Min Act: 0.0000

Data Index: 1579998 (The Pile)

Max Activating Token Index: 345

Text #10

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.3422. Min Act: -0.0000

Data Index: 1137842 (The Pile)

Max Activating Token Index: 649

Text #11

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.3340. Min Act: 0.0000

Data Index: 860866 (The Pile)

Max Activating Token Index: 880

Text #12

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.3190. Min Act: -0.0000

Data Index: 493905 (The Pile)

Max Activating Token Index: 772

Text #13

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.3439. Min Act: -0.0000

Data Index: 1217445 (The Pile)

Max Activating Token Index: 165

Text #14

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.3398. Min Act: -0.0000

Data Index: 1381595 (The Pile)

Max Activating Token Index: 424

Text #15

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.3181. Min Act: 0.0000

Data Index: 1636944 (The Pile)

Max Activating Token Index: 229

Text #16

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.3255. Min Act: -0.0000

Data Index: 1088274 (The Pile)

Max Activating Token Index: 173

Text #17

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.3161. Min Act: 0.0000

Data Index: 549897 (The Pile)

Max Activating Token Index: 834

Text #18

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.3195. Min Act: 0.0000

Data Index: 1231897 (The Pile)

Max Activating Token Index: 139

Text #19

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.2973. Min Act: 0.0000

Data Index: 1219314 (The Pile)

Max Activating Token Index: 817