Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 238 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1165. Min Act: -0.0006

Data Index: 159899 (C4 (Web Text))

Max Activating Token Index: 315

Text #1

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1296. Min Act: -0.0006

Data Index: 1294156 (C4 (Web Text))

Max Activating Token Index: 620

Text #2

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1262. Min Act: -0.0006

Data Index: 1003145 (C4 (Web Text))

Max Activating Token Index: 303

Text #3

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1078. Min Act: -0.0006

Data Index: 732600 (C4 (Web Text))

Max Activating Token Index: 629

Text #4

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1109. Min Act: -0.0006

Data Index: 307151 (C4 (Web Text))

Max Activating Token Index: 490

Text #5

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1148. Min Act: -0.0006

Data Index: 576068 (C4 (Web Text))

Max Activating Token Index: 638

Text #6

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1196. Min Act: -0.0006

Data Index: 530098 (C4 (Web Text))

Max Activating Token Index: 384

Text #7

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1147. Min Act: -0.0006

Data Index: 406307 (C4 (Web Text))

Max Activating Token Index: 317

Text #8

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1193. Min Act: -0.0006

Data Index: 1357307 (C4 (Web Text))

Max Activating Token Index: 585

Text #9

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1038. Min Act: -0.0006

Data Index: 591577 (C4 (Web Text))

Max Activating Token Index: 670

Text #10

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1172. Min Act: -0.0006

Data Index: 167931 (C4 (Web Text))

Max Activating Token Index: 1014

Text #11

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1084. Min Act: -0.0006

Data Index: 644792 (C4 (Web Text))

Max Activating Token Index: 637

Text #12

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1073. Min Act: -0.0006

Data Index: 774840 (C4 (Web Text))

Max Activating Token Index: 352

Text #13

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1115. Min Act: -0.0006

Data Index: 234711 (C4 (Web Text))

Max Activating Token Index: 414

Text #14

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1063. Min Act: -0.0006

Data Index: 1038282 (C4 (Web Text))

Max Activating Token Index: 461

Text #15

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1139. Min Act: -0.0006

Data Index: 857151 (C4 (Web Text))

Max Activating Token Index: 451

Text #16

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1101. Min Act: -0.0006

Data Index: 842968 (C4 (Web Text))

Max Activating Token Index: 313

Text #17

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1235. Min Act: -0.0006

Data Index: 1068148 (C4 (Web Text))

Max Activating Token Index: 296

Text #18

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1137. Min Act: -0.0006

Data Index: 158052 (C4 (Web Text))

Max Activating Token Index: 349

Text #19

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1015. Min Act: -0.0006

Data Index: 993797 (C4 (Web Text))

Max Activating Token Index: 617