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

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

Neuron 3862 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: 1.0391. Min Range: -1.0391

Max Act: 1.0078. Min Act: -0.0000

Data Index: 363851 (C4 (Web Text))

Max Activating Token Index: 747

Text #1

Max Range: 1.0391. Min Range: -1.0391

Max Act: 1.0391. Min Act: -0.0000

Data Index: 1086555 (C4 (Web Text))

Max Activating Token Index: 254

Text #2

Max Range: 1.0391. Min Range: -1.0391

Max Act: 0.9600. Min Act: -0.0000

Data Index: 280489 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 1.0391. Min Range: -1.0391

Max Act: 0.8877. Min Act: -0.0000

Data Index: 491467 (C4 (Web Text))

Max Activating Token Index: 552

Text #4

Max Range: 1.0391. Min Range: -1.0391

Max Act: 0.9734. Min Act: -0.0000

Data Index: 798523 (C4 (Web Text))

Max Activating Token Index: 196

Text #5

Max Range: 1.0391. Min Range: -1.0391

Max Act: 0.9206. Min Act: -0.0000

Data Index: 1216 (C4 (Web Text))

Max Activating Token Index: 313

Text #6

Max Range: 1.0391. Min Range: -1.0391

Max Act: 0.9660. Min Act: -0.0000

Data Index: 223233 (C4 (Web Text))

Max Activating Token Index: 823

Text #7

Max Range: 1.0391. Min Range: -1.0391

Max Act: 0.9024. Min Act: -0.0000

Data Index: 713248 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 1.0391. Min Range: -1.0391

Max Act: 0.8825. Min Act: -0.0000

Data Index: 1345479 (C4 (Web Text))

Max Activating Token Index: 356

Text #9

Max Range: 1.0391. Min Range: -1.0391

Max Act: 0.8818. Min Act: -0.0000

Data Index: 1221470 (C4 (Web Text))

Max Activating Token Index: 693

Text #10

Max Range: 1.0391. Min Range: -1.0391

Max Act: 0.8388. Min Act: -0.0000

Data Index: 968103 (C4 (Web Text))

Max Activating Token Index: 383

Text #11

Max Range: 1.0391. Min Range: -1.0391

Max Act: 0.8579. Min Act: -0.0000

Data Index: 473239 (C4 (Web Text))

Max Activating Token Index: 329

Text #12

Max Range: 1.0391. Min Range: -1.0391

Max Act: 0.8477. Min Act: -0.0000

Data Index: 790418 (C4 (Web Text))

Max Activating Token Index: 867

Text #13

Max Range: 1.0391. Min Range: -1.0391

Max Act: 0.8346. Min Act: -0.0000

Data Index: 517008 (C4 (Web Text))

Max Activating Token Index: 892

Text #14

Max Range: 1.0391. Min Range: -1.0391

Max Act: 0.8279. Min Act: -0.0000

Data Index: 623196 (C4 (Web Text))

Max Activating Token Index: 689

Text #15

Max Range: 1.0391. Min Range: -1.0391

Max Act: 0.8295. Min Act: -0.0000

Data Index: 1166913 (C4 (Web Text))

Max Activating Token Index: 228

Text #16

Max Range: 1.0391. Min Range: -1.0391

Max Act: 0.8194. Min Act: -0.0000

Data Index: 230961 (C4 (Web Text))

Max Activating Token Index: 86

Text #17

Max Range: 1.0391. Min Range: -1.0391

Max Act: 0.8177. Min Act: -0.0000

Data Index: 194916 (C4 (Web Text))

Max Activating Token Index: 996

Text #18

Max Range: 1.0391. Min Range: -1.0391

Max Act: 0.7587. Min Act: -0.0000

Data Index: 567507 (C4 (Web Text))

Max Activating Token Index: 81

Text #19

Max Range: 1.0391. Min Range: -1.0391

Max Act: 0.7966. Min Act: -0.0000

Data Index: 343882 (C4 (Web Text))

Max Activating Token Index: 830