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

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

Neuron 503 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1391. Min Range: -0.1391

Max Act: 0.1391. Min Act: -0.0001

Data Index: 625634 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 0.1391. Min Range: -0.1391

Max Act: 0.1282. Min Act: -0.0001

Data Index: 938791 (C4 (Web Text))

Max Activating Token Index: 214

Text #2

Max Range: 0.1391. Min Range: -0.1391

Max Act: 0.1305. Min Act: -0.0001

Data Index: 317157 (C4 (Web Text))

Max Activating Token Index: 247

Text #3

Max Range: 0.1391. Min Range: -0.1391

Max Act: 0.1315. Min Act: -0.0001

Data Index: 549896 (C4 (Web Text))

Max Activating Token Index: 132

Text #4

Max Range: 0.1391. Min Range: -0.1391

Max Act: 0.1272. Min Act: -0.0001

Data Index: 541116 (C4 (Web Text))

Max Activating Token Index: 667

Text #5

Max Range: 0.1391. Min Range: -0.1391

Max Act: 0.1318. Min Act: -0.0001

Data Index: 504152 (C4 (Web Text))

Max Activating Token Index: 482

Text #6

Max Range: 0.1391. Min Range: -0.1391

Max Act: 0.1189. Min Act: -0.0001

Data Index: 349779 (C4 (Web Text))

Max Activating Token Index: 35

Text #7

Max Range: 0.1391. Min Range: -0.1391

Max Act: 0.1161. Min Act: -0.0001

Data Index: 314650 (C4 (Web Text))

Max Activating Token Index: 782

Text #8

Max Range: 0.1391. Min Range: -0.1391

Max Act: 0.1212. Min Act: -0.0001

Data Index: 665426 (C4 (Web Text))

Max Activating Token Index: 229

Text #9

Max Range: 0.1391. Min Range: -0.1391

Max Act: 0.1177. Min Act: -0.0001

Data Index: 380843 (C4 (Web Text))

Max Activating Token Index: 457

Text #10

Max Range: 0.1391. Min Range: -0.1391

Max Act: 0.1174. Min Act: -0.0001

Data Index: 763082 (C4 (Web Text))

Max Activating Token Index: 532

Text #11

Max Range: 0.1391. Min Range: -0.1391

Max Act: 0.1097. Min Act: -0.0001

Data Index: 18279 (C4 (Web Text))

Max Activating Token Index: 696

Text #12

Max Range: 0.1391. Min Range: -0.1391

Max Act: 0.1211. Min Act: -0.0001

Data Index: 1264028 (C4 (Web Text))

Max Activating Token Index: 607

Text #13

Max Range: 0.1391. Min Range: -0.1391

Max Act: 0.1091. Min Act: -0.0001

Data Index: 117970 (C4 (Web Text))

Max Activating Token Index: 703

Text #14

Max Range: 0.1391. Min Range: -0.1391

Max Act: 0.1124. Min Act: -0.0001

Data Index: 248685 (C4 (Web Text))

Max Activating Token Index: 14

Text #15

Max Range: 0.1391. Min Range: -0.1391

Max Act: 0.1079. Min Act: -0.0001

Data Index: 974232 (C4 (Web Text))

Max Activating Token Index: 224

Text #16

Max Range: 0.1391. Min Range: -0.1391

Max Act: 0.1166. Min Act: -0.0001

Data Index: 1289050 (C4 (Web Text))

Max Activating Token Index: 536

Text #17

Max Range: 0.1391. Min Range: -0.1391

Max Act: 0.1150. Min Act: -0.0001

Data Index: 365787 (C4 (Web Text))

Max Activating Token Index: 110

Text #18

Max Range: 0.1391. Min Range: -0.1391

Max Act: 0.1098. Min Act: -0.0001

Data Index: 1194540 (C4 (Web Text))

Max Activating Token Index: 380

Text #19

Max Range: 0.1391. Min Range: -0.1391

Max Act: 0.1098. Min Act: -0.0001

Data Index: 194690 (C4 (Web Text))

Max Activating Token Index: 636