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

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

Neuron 4206 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7156. Min Range: -1.7156

Max Act: 1.7121. Min Act: -0.0001

Data Index: 1081517 (C4 (Web Text))

Max Activating Token Index: 293

Text #1

Max Range: 1.7156. Min Range: -1.7156

Max Act: 1.6966. Min Act: -0.0001

Data Index: 20500 (C4 (Web Text))

Max Activating Token Index: 916

Text #2

Max Range: 1.7156. Min Range: -1.7156

Max Act: 1.7156. Min Act: -0.0001

Data Index: 535923 (C4 (Web Text))

Max Activating Token Index: 365

Text #3

Max Range: 1.7156. Min Range: -1.7156

Max Act: 1.6768. Min Act: -0.0001

Data Index: 1062818 (C4 (Web Text))

Max Activating Token Index: 452

Text #4

Max Range: 1.7156. Min Range: -1.7156

Max Act: 1.5078. Min Act: -0.0001

Data Index: 930683 (C4 (Web Text))

Max Activating Token Index: 928

Text #5

Max Range: 1.7156. Min Range: -1.7156

Max Act: 1.6027. Min Act: -0.0001

Data Index: 68103 (C4 (Web Text))

Max Activating Token Index: 845

Text #6

Max Range: 1.7156. Min Range: -1.7156

Max Act: 1.5312. Min Act: -0.0001

Data Index: 610480 (C4 (Web Text))

Max Activating Token Index: 836

Text #7

Max Range: 1.7156. Min Range: -1.7156

Max Act: 1.6121. Min Act: -0.0001

Data Index: 1013395 (C4 (Web Text))

Max Activating Token Index: 567

Text #8

Max Range: 1.7156. Min Range: -1.7156

Max Act: 1.4978. Min Act: -0.0001

Data Index: 1133757 (C4 (Web Text))

Max Activating Token Index: 797

Text #9

Max Range: 1.7156. Min Range: -1.7156

Max Act: 1.5934. Min Act: -0.0001

Data Index: 76347 (C4 (Web Text))

Max Activating Token Index: 903

Text #10

Max Range: 1.7156. Min Range: -1.7156

Max Act: 1.6809. Min Act: -0.0001

Data Index: 298458 (C4 (Web Text))

Max Activating Token Index: 99

Text #11

Max Range: 1.7156. Min Range: -1.7156

Max Act: 1.4157. Min Act: -0.0001

Data Index: 184367 (C4 (Web Text))

Max Activating Token Index: 859

Text #12

Max Range: 1.7156. Min Range: -1.7156

Max Act: 1.4846. Min Act: -0.0001

Data Index: 390557 (C4 (Web Text))

Max Activating Token Index: 296

Text #13

Max Range: 1.7156. Min Range: -1.7156

Max Act: 1.4765. Min Act: -0.0001

Data Index: 1012413 (C4 (Web Text))

Max Activating Token Index: 333

Text #14

Max Range: 1.7156. Min Range: -1.7156

Max Act: 1.6317. Min Act: -0.0001

Data Index: 556610 (C4 (Web Text))

Max Activating Token Index: 93

Text #15

Max Range: 1.7156. Min Range: -1.7156

Max Act: 1.5058. Min Act: -0.0001

Data Index: 600064 (C4 (Web Text))

Max Activating Token Index: 626

Text #16

Max Range: 1.7156. Min Range: -1.7156

Max Act: 1.6971. Min Act: -0.0001

Data Index: 178016 (C4 (Web Text))

Max Activating Token Index: 218

Text #17

Max Range: 1.7156. Min Range: -1.7156

Max Act: 1.6277. Min Act: -0.0001

Data Index: 216851 (C4 (Web Text))

Max Activating Token Index: 425

Text #18

Max Range: 1.7156. Min Range: -1.7156

Max Act: 1.5443. Min Act: -0.0001

Data Index: 1164613 (C4 (Web Text))

Max Activating Token Index: 690

Text #19

Max Range: 1.7156. Min Range: -1.7156

Max Act: 1.5463. Min Act: -0.0001

Data Index: 235579 (C4 (Web Text))

Max Activating Token Index: 669