Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4578 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5549. Min Range: -1.5549

Max Act: 1.5501. Min Act: -0.0000

Data Index: 1217986 (C4 (Web Text))

Max Activating Token Index: 719

Text #1

Max Range: 1.5549. Min Range: -1.5549

Max Act: 1.4313. Min Act: -0.0000

Data Index: 296571 (C4 (Web Text))

Max Activating Token Index: 935

Text #2

Max Range: 1.5549. Min Range: -1.5549

Max Act: 1.5133. Min Act: -0.0000

Data Index: 541074 (C4 (Web Text))

Max Activating Token Index: 765

Text #3

Max Range: 1.5549. Min Range: -1.5549

Max Act: 1.5065. Min Act: -0.0000

Data Index: 1285667 (C4 (Web Text))

Max Activating Token Index: 136

Text #4

Max Range: 1.5549. Min Range: -1.5549

Max Act: 1.4910. Min Act: -0.0000

Data Index: 544415 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 1.5549. Min Range: -1.5549

Max Act: 1.5549. Min Act: -0.0000

Data Index: 833326 (C4 (Web Text))

Max Activating Token Index: 975

Text #6

Max Range: 1.5549. Min Range: -1.5549

Max Act: 1.3896. Min Act: -0.0000

Data Index: 998746 (C4 (Web Text))

Max Activating Token Index: 887

Text #7

Max Range: 1.5549. Min Range: -1.5549

Max Act: 1.3351. Min Act: -0.0000

Data Index: 367125 (C4 (Web Text))

Max Activating Token Index: 560

Text #8

Max Range: 1.5549. Min Range: -1.5549

Max Act: 1.3254. Min Act: -0.0000

Data Index: 898044 (C4 (Web Text))

Max Activating Token Index: 613

Text #9

Max Range: 1.5549. Min Range: -1.5549

Max Act: 1.3226. Min Act: -0.0000

Data Index: 578992 (C4 (Web Text))

Max Activating Token Index: 173

Text #10

Max Range: 1.5549. Min Range: -1.5549

Max Act: 1.3725. Min Act: -0.0000

Data Index: 993994 (C4 (Web Text))

Max Activating Token Index: 363

Text #11

Max Range: 1.5549. Min Range: -1.5549

Max Act: 1.2759. Min Act: -0.0000

Data Index: 315056 (C4 (Web Text))

Max Activating Token Index: 1015

Text #12

Max Range: 1.5549. Min Range: -1.5549

Max Act: 1.2492. Min Act: -0.0000

Data Index: 1173402 (C4 (Web Text))

Max Activating Token Index: 701

Text #13

Max Range: 1.5549. Min Range: -1.5549

Max Act: 1.2382. Min Act: -0.0000

Data Index: 139304 (C4 (Web Text))

Max Activating Token Index: 141

Text #14

Max Range: 1.5549. Min Range: -1.5549

Max Act: 1.2273. Min Act: -0.0000

Data Index: 147063 (C4 (Web Text))

Max Activating Token Index: 807

Text #15

Max Range: 1.5549. Min Range: -1.5549

Max Act: 1.2164. Min Act: -0.0000

Data Index: 850386 (C4 (Web Text))

Max Activating Token Index: 116

Text #16

Max Range: 1.5549. Min Range: -1.5549

Max Act: 1.2036. Min Act: -0.0000

Data Index: 1001070 (C4 (Web Text))

Max Activating Token Index: 975

Text #17

Max Range: 1.5549. Min Range: -1.5549

Max Act: 1.1345. Min Act: -0.0000

Data Index: 1147686 (C4 (Web Text))

Max Activating Token Index: 835

Text #18

Max Range: 1.5549. Min Range: -1.5549

Max Act: 1.1969. Min Act: -0.0000

Data Index: 133938 (C4 (Web Text))

Max Activating Token Index: 740

Text #19

Max Range: 1.5549. Min Range: -1.5549

Max Act: 1.1207. Min Act: -0.0000

Data Index: 1098154 (C4 (Web Text))

Max Activating Token Index: 213