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

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

Neuron 2923 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9397. Min Range: -0.9397

Max Act: 0.9397. Min Act: -0.0001

Data Index: 433672 (C4 (Web Text))

Max Activating Token Index: 88

Text #1

Max Range: 0.9397. Min Range: -0.9397

Max Act: 0.8462. Min Act: -0.0001

Data Index: 1163081 (C4 (Web Text))

Max Activating Token Index: 658

Text #2

Max Range: 0.9397. Min Range: -0.9397

Max Act: 0.7004. Min Act: -0.0000

Data Index: 814228 (C4 (Web Text))

Max Activating Token Index: 634

Text #3

Max Range: 0.9397. Min Range: -0.9397

Max Act: 0.7247. Min Act: -0.0000

Data Index: 1112087 (C4 (Web Text))

Max Activating Token Index: 175

Text #4

Max Range: 0.9397. Min Range: -0.9397

Max Act: 0.7194. Min Act: -0.0000

Data Index: 1338410 (C4 (Web Text))

Max Activating Token Index: 870

Text #5

Max Range: 0.9397. Min Range: -0.9397

Max Act: 0.6888. Min Act: -0.0001

Data Index: 1300204 (C4 (Web Text))

Max Activating Token Index: 406

Text #6

Max Range: 0.9397. Min Range: -0.9397

Max Act: 0.6733. Min Act: -0.0000

Data Index: 1256690 (C4 (Web Text))

Max Activating Token Index: 575

Text #7

Max Range: 0.9397. Min Range: -0.9397

Max Act: 0.6673. Min Act: -0.0000

Data Index: 1003050 (C4 (Web Text))

Max Activating Token Index: 344

Text #8

Max Range: 0.9397. Min Range: -0.9397

Max Act: 0.6571. Min Act: -0.0001

Data Index: 997112 (C4 (Web Text))

Max Activating Token Index: 814

Text #9

Max Range: 0.9397. Min Range: -0.9397

Max Act: 0.6898. Min Act: -0.0000

Data Index: 1169630 (C4 (Web Text))

Max Activating Token Index: 769

Text #10

Max Range: 0.9397. Min Range: -0.9397

Max Act: 0.6824. Min Act: -0.0000

Data Index: 861522 (C4 (Web Text))

Max Activating Token Index: 298

Text #11

Max Range: 0.9397. Min Range: -0.9397

Max Act: 0.6557. Min Act: -0.0000

Data Index: 746929 (C4 (Web Text))

Max Activating Token Index: 691

Text #12

Max Range: 0.9397. Min Range: -0.9397

Max Act: 0.6626. Min Act: -0.0000

Data Index: 676586 (C4 (Web Text))

Max Activating Token Index: 550

Text #13

Max Range: 0.9397. Min Range: -0.9397

Max Act: 0.6093. Min Act: -0.0000

Data Index: 825811 (C4 (Web Text))

Max Activating Token Index: 206

Text #14

Max Range: 0.9397. Min Range: -0.9397

Max Act: 0.5942. Min Act: -0.0000

Data Index: 227268 (C4 (Web Text))

Max Activating Token Index: 760

Text #15

Max Range: 0.9397. Min Range: -0.9397

Max Act: 0.5865. Min Act: -0.0000

Data Index: 362529 (C4 (Web Text))

Max Activating Token Index: 860

Text #16

Max Range: 0.9397. Min Range: -0.9397

Max Act: 0.6190. Min Act: -0.0000

Data Index: 154301 (C4 (Web Text))

Max Activating Token Index: 348

Text #17

Max Range: 0.9397. Min Range: -0.9397

Max Act: 0.5778. Min Act: -0.0000

Data Index: 426784 (C4 (Web Text))

Max Activating Token Index: 525

Text #18

Max Range: 0.9397. Min Range: -0.9397

Max Act: 0.6001. Min Act: -0.0001

Data Index: 1250754 (C4 (Web Text))

Max Activating Token Index: 144

Text #19

Max Range: 0.9397. Min Range: -0.9397

Max Act: 0.5929. Min Act: -0.0000

Data Index: 73091 (C4 (Web Text))

Max Activating Token Index: 537