Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 133 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1371. Min Act: -0.0001

Data Index: 518587 (C4 (Web Text))

Max Activating Token Index: 77

Text #1

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1275. Min Act: -0.0002

Data Index: 487818 (C4 (Web Text))

Max Activating Token Index: 937

Text #2

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1364. Min Act: -0.0001

Data Index: 349118 (C4 (Web Text))

Max Activating Token Index: 474

Text #3

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1295. Min Act: -0.0001

Data Index: 193534 (C4 (Web Text))

Max Activating Token Index: 157

Text #4

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1226. Min Act: -0.0002

Data Index: 79459 (C4 (Web Text))

Max Activating Token Index: 629

Text #5

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1228. Min Act: -0.0001

Data Index: 711154 (C4 (Web Text))

Max Activating Token Index: 904

Text #6

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1185. Min Act: -0.0001

Data Index: 584522 (C4 (Web Text))

Max Activating Token Index: 268

Text #7

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1205. Min Act: -0.0001

Data Index: 750213 (C4 (Web Text))

Max Activating Token Index: 824

Text #8

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1161. Min Act: -0.0002

Data Index: 617902 (C4 (Web Text))

Max Activating Token Index: 335

Text #9

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1253. Min Act: -0.0001

Data Index: 62361 (C4 (Web Text))

Max Activating Token Index: 693

Text #10

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1152. Min Act: -0.0001

Data Index: 617355 (C4 (Web Text))

Max Activating Token Index: 703

Text #11

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1173. Min Act: -0.0001

Data Index: 1022169 (C4 (Web Text))

Max Activating Token Index: 413

Text #12

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1076. Min Act: -0.0001

Data Index: 872251 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1201. Min Act: -0.0001

Data Index: 1131185 (C4 (Web Text))

Max Activating Token Index: 431

Text #14

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1178. Min Act: -0.0001

Data Index: 38334 (C4 (Web Text))

Max Activating Token Index: 133

Text #15

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1211. Min Act: -0.0001

Data Index: 508517 (C4 (Web Text))

Max Activating Token Index: 344

Text #16

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1142. Min Act: -0.0001

Data Index: 1136390 (C4 (Web Text))

Max Activating Token Index: 400

Text #17

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1142. Min Act: -0.0001

Data Index: 153616 (C4 (Web Text))

Max Activating Token Index: 697

Text #18

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1134. Min Act: -0.0001

Data Index: 1131834 (C4 (Web Text))

Max Activating Token Index: 514

Text #19

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1067. Min Act: -0.0001

Data Index: 845201 (C4 (Web Text))

Max Activating Token Index: 684