Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 96 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1474. Min Act: -0.0001

Data Index: 113148 (C4 (Web Text))

Max Activating Token Index: 532

Text #1

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1325. Min Act: -0.0001

Data Index: 1186809 (C4 (Web Text))

Max Activating Token Index: 596

Text #2

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1390. Min Act: -0.0001

Data Index: 110302 (C4 (Web Text))

Max Activating Token Index: 554

Text #3

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1330. Min Act: -0.0001

Data Index: 1291814 (C4 (Web Text))

Max Activating Token Index: 933

Text #4

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1345. Min Act: -0.0001

Data Index: 1334781 (C4 (Web Text))

Max Activating Token Index: 390

Text #5

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1269. Min Act: -0.0001

Data Index: 129241 (C4 (Web Text))

Max Activating Token Index: 660

Text #6

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1210. Min Act: -0.0001

Data Index: 123842 (C4 (Web Text))

Max Activating Token Index: 394

Text #7

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1222. Min Act: -0.0001

Data Index: 264452 (C4 (Web Text))

Max Activating Token Index: 929

Text #8

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1226. Min Act: -0.0001

Data Index: 200358 (C4 (Web Text))

Max Activating Token Index: 95

Text #9

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1260. Min Act: -0.0001

Data Index: 171260 (C4 (Web Text))

Max Activating Token Index: 442

Text #10

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1199. Min Act: -0.0001

Data Index: 686817 (C4 (Web Text))

Max Activating Token Index: 145

Text #11

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1150. Min Act: -0.0001

Data Index: 98877 (C4 (Web Text))

Max Activating Token Index: 851

Text #12

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1152. Min Act: -0.0001

Data Index: 791716 (C4 (Web Text))

Max Activating Token Index: 714

Text #13

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1152. Min Act: -0.0001

Data Index: 78462 (C4 (Web Text))

Max Activating Token Index: 650

Text #14

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1076. Min Act: -0.0001

Data Index: 1116922 (C4 (Web Text))

Max Activating Token Index: 981

Text #15

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1156. Min Act: -0.0001

Data Index: 1247206 (C4 (Web Text))

Max Activating Token Index: 33

Text #16

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1142. Min Act: -0.0001

Data Index: 873606 (C4 (Web Text))

Max Activating Token Index: 547

Text #17

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1070. Min Act: -0.0001

Data Index: 550211 (C4 (Web Text))

Max Activating Token Index: 790

Text #18

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1102. Min Act: -0.0001

Data Index: 469358 (C4 (Web Text))

Max Activating Token Index: 766

Text #19

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1172. Min Act: -0.0001

Data Index: 42145 (C4 (Web Text))

Max Activating Token Index: 888