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

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

Neuron 3815 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9409. Min Range: -0.9409

Max Act: 0.9409. Min Act: -0.0000

Data Index: 831761 (C4 (Web Text))

Max Activating Token Index: 75

Text #1

Max Range: 0.9409. Min Range: -0.9409

Max Act: 0.8442. Min Act: -0.0000

Data Index: 702893 (C4 (Web Text))

Max Activating Token Index: 506

Text #2

Max Range: 0.9409. Min Range: -0.9409

Max Act: 0.8189. Min Act: -0.0000

Data Index: 681429 (C4 (Web Text))

Max Activating Token Index: 701

Text #3

Max Range: 0.9409. Min Range: -0.9409

Max Act: 0.7590. Min Act: -0.0000

Data Index: 408847 (C4 (Web Text))

Max Activating Token Index: 426

Text #4

Max Range: 0.9409. Min Range: -0.9409

Max Act: 0.7720. Min Act: -0.0000

Data Index: 419810 (C4 (Web Text))

Max Activating Token Index: 938

Text #5

Max Range: 0.9409. Min Range: -0.9409

Max Act: 0.7057. Min Act: -0.0000

Data Index: 1067301 (C4 (Web Text))

Max Activating Token Index: 827

Text #6

Max Range: 0.9409. Min Range: -0.9409

Max Act: 0.6971. Min Act: -0.0000

Data Index: 965291 (C4 (Web Text))

Max Activating Token Index: 644

Text #7

Max Range: 0.9409. Min Range: -0.9409

Max Act: 0.7362. Min Act: -0.0000

Data Index: 422549 (C4 (Web Text))

Max Activating Token Index: 223

Text #8

Max Range: 0.9409. Min Range: -0.9409

Max Act: 0.7239. Min Act: -0.0000

Data Index: 622893 (C4 (Web Text))

Max Activating Token Index: 189

Text #9

Max Range: 0.9409. Min Range: -0.9409

Max Act: 0.6760. Min Act: -0.0000

Data Index: 884143 (C4 (Web Text))

Max Activating Token Index: 269

Text #10

Max Range: 0.9409. Min Range: -0.9409

Max Act: 0.7173. Min Act: -0.0000

Data Index: 671411 (C4 (Web Text))

Max Activating Token Index: 134

Text #11

Max Range: 0.9409. Min Range: -0.9409

Max Act: 0.7119. Min Act: -0.0000

Data Index: 205851 (C4 (Web Text))

Max Activating Token Index: 891

Text #12

Max Range: 0.9409. Min Range: -0.9409

Max Act: 0.7102. Min Act: -0.0000

Data Index: 367370 (C4 (Web Text))

Max Activating Token Index: 552

Text #13

Max Range: 0.9409. Min Range: -0.9409

Max Act: 0.7044. Min Act: 0.0000

Data Index: 170878 (C4 (Web Text))

Max Activating Token Index: 691

Text #14

Max Range: 0.9409. Min Range: -0.9409

Max Act: 0.6941. Min Act: -0.0000

Data Index: 603198 (C4 (Web Text))

Max Activating Token Index: 209

Text #15

Max Range: 0.9409. Min Range: -0.9409

Max Act: 0.6830. Min Act: -0.0000

Data Index: 787022 (C4 (Web Text))

Max Activating Token Index: 964

Text #16

Max Range: 0.9409. Min Range: -0.9409

Max Act: 0.6837. Min Act: -0.0000

Data Index: 1094605 (C4 (Web Text))

Max Activating Token Index: 837

Text #17

Max Range: 0.9409. Min Range: -0.9409

Max Act: 0.6833. Min Act: -0.0000

Data Index: 112018 (C4 (Web Text))

Max Activating Token Index: 576

Text #18

Max Range: 0.9409. Min Range: -0.9409

Max Act: 0.6297. Min Act: -0.0000

Data Index: 491346 (C4 (Web Text))

Max Activating Token Index: 823

Text #19

Max Range: 0.9409. Min Range: -0.9409

Max Act: 0.6735. Min Act: -0.0000

Data Index: 988165 (C4 (Web Text))

Max Activating Token Index: 111