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

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

Neuron 3453 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8352. Min Range: -1.8352

Max Act: 1.8231. Min Act: -0.0000

Data Index: 922172 (C4 (Web Text))

Max Activating Token Index: 602

Text #1

Max Range: 1.8352. Min Range: -1.8352

Max Act: 1.7024. Min Act: -0.0000

Data Index: 965627 (C4 (Web Text))

Max Activating Token Index: 274

Text #2

Max Range: 1.8352. Min Range: -1.8352

Max Act: 1.8352. Min Act: -0.0000

Data Index: 646116 (C4 (Web Text))

Max Activating Token Index: 369

Text #3

Max Range: 1.8352. Min Range: -1.8352

Max Act: 1.5821. Min Act: -0.0000

Data Index: 742539 (C4 (Web Text))

Max Activating Token Index: 956

Text #4

Max Range: 1.8352. Min Range: -1.8352

Max Act: 1.4767. Min Act: -0.0000

Data Index: 1288256 (C4 (Web Text))

Max Activating Token Index: 817

Text #5

Max Range: 1.8352. Min Range: -1.8352

Max Act: 1.4510. Min Act: -0.0000

Data Index: 1117877 (C4 (Web Text))

Max Activating Token Index: 126

Text #6

Max Range: 1.8352. Min Range: -1.8352

Max Act: 1.6378. Min Act: -0.0000

Data Index: 725599 (C4 (Web Text))

Max Activating Token Index: 236

Text #7

Max Range: 1.8352. Min Range: -1.8352

Max Act: 1.4085. Min Act: -0.0000

Data Index: 675524 (C4 (Web Text))

Max Activating Token Index: 138

Text #8

Max Range: 1.8352. Min Range: -1.8352

Max Act: 1.5651. Min Act: -0.0000

Data Index: 190175 (C4 (Web Text))

Max Activating Token Index: 629

Text #9

Max Range: 1.8352. Min Range: -1.8352

Max Act: 1.4473. Min Act: -0.0000

Data Index: 1278607 (C4 (Web Text))

Max Activating Token Index: 409

Text #10

Max Range: 1.8352. Min Range: -1.8352

Max Act: 1.3410. Min Act: -0.0000

Data Index: 812560 (C4 (Web Text))

Max Activating Token Index: 887

Text #11

Max Range: 1.8352. Min Range: -1.8352

Max Act: 1.4281. Min Act: -0.0000

Data Index: 861803 (C4 (Web Text))

Max Activating Token Index: 138

Text #12

Max Range: 1.8352. Min Range: -1.8352

Max Act: 1.3091. Min Act: -0.0000

Data Index: 433696 (C4 (Web Text))

Max Activating Token Index: 816

Text #13

Max Range: 1.8352. Min Range: -1.8352

Max Act: 1.1749. Min Act: -0.0000

Data Index: 383477 (C4 (Web Text))

Max Activating Token Index: 229

Text #14

Max Range: 1.8352. Min Range: -1.8352

Max Act: 1.2442. Min Act: -0.0000

Data Index: 581178 (C4 (Web Text))

Max Activating Token Index: 532

Text #15

Max Range: 1.8352. Min Range: -1.8352

Max Act: 1.0906. Min Act: -0.0000

Data Index: 340592 (C4 (Web Text))

Max Activating Token Index: 191

Text #16

Max Range: 1.8352. Min Range: -1.8352

Max Act: 1.1237. Min Act: -0.0000

Data Index: 453801 (C4 (Web Text))

Max Activating Token Index: 762

Text #17

Max Range: 1.8352. Min Range: -1.8352

Max Act: 1.2678. Min Act: -0.0000

Data Index: 1027820 (C4 (Web Text))

Max Activating Token Index: 169

Text #18

Max Range: 1.8352. Min Range: -1.8352

Max Act: 1.2161. Min Act: -0.0000

Data Index: 85505 (C4 (Web Text))

Max Activating Token Index: 576

Text #19

Max Range: 1.8352. Min Range: -1.8352

Max Act: 1.3467. Min Act: -0.0000

Data Index: 528762 (C4 (Web Text))

Max Activating Token Index: 314