Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2001 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1414. Min Act: -0.0002

Data Index: 205702 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1368. Min Act: -0.0002

Data Index: 448061 (C4 (Web Text))

Max Activating Token Index: 413

Text #2

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1267. Min Act: -0.0002

Data Index: 1262210 (C4 (Web Text))

Max Activating Token Index: 68

Text #3

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1250. Min Act: -0.0002

Data Index: 1191539 (C4 (Web Text))

Max Activating Token Index: 25

Text #4

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1224. Min Act: -0.0002

Data Index: 325312 (C4 (Web Text))

Max Activating Token Index: 962

Text #5

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1301. Min Act: -0.0002

Data Index: 588629 (C4 (Web Text))

Max Activating Token Index: 366

Text #6

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1266. Min Act: -0.0002

Data Index: 1061511 (C4 (Web Text))

Max Activating Token Index: 271

Text #7

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1218. Min Act: -0.0002

Data Index: 783755 (C4 (Web Text))

Max Activating Token Index: 569

Text #8

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1230. Min Act: -0.0002

Data Index: 1257961 (C4 (Web Text))

Max Activating Token Index: 961

Text #9

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1190. Min Act: -0.0002

Data Index: 297448 (C4 (Web Text))

Max Activating Token Index: 912

Text #10

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1211. Min Act: -0.0002

Data Index: 1202947 (C4 (Web Text))

Max Activating Token Index: 807

Text #11

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1185. Min Act: -0.0002

Data Index: 632960 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1187. Min Act: -0.0002

Data Index: 1151141 (C4 (Web Text))

Max Activating Token Index: 63

Text #13

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1235. Min Act: -0.0002

Data Index: 356041 (C4 (Web Text))

Max Activating Token Index: 244

Text #14

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1206. Min Act: -0.0002

Data Index: 905558 (C4 (Web Text))

Max Activating Token Index: 817

Text #15

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1112. Min Act: -0.0002

Data Index: 368870 (C4 (Web Text))

Max Activating Token Index: 346

Text #16

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1110. Min Act: -0.0002

Data Index: 474299 (C4 (Web Text))

Max Activating Token Index: 198

Text #17

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1197. Min Act: -0.0002

Data Index: 1134185 (C4 (Web Text))

Max Activating Token Index: 723

Text #18

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1244. Min Act: -0.0002

Data Index: 1114880 (C4 (Web Text))

Max Activating Token Index: 828

Text #19

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1229. Min Act: -0.0002

Data Index: 329495 (C4 (Web Text))

Max Activating Token Index: 60