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

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

Neuron 2121 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1511. Min Act: -0.0001

Data Index: 1243137 (C4 (Web Text))

Max Activating Token Index: 850

Text #1

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1446. Min Act: -0.0001

Data Index: 436281 (C4 (Web Text))

Max Activating Token Index: 349

Text #2

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1527. Min Act: -0.0001

Data Index: 281108 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1338. Min Act: -0.0001

Data Index: 378663 (C4 (Web Text))

Max Activating Token Index: 761

Text #4

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1282. Min Act: -0.0001

Data Index: 1186965 (C4 (Web Text))

Max Activating Token Index: 700

Text #5

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1382. Min Act: -0.0001

Data Index: 158213 (C4 (Web Text))

Max Activating Token Index: 793

Text #6

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1281. Min Act: -0.0001

Data Index: 614038 (C4 (Web Text))

Max Activating Token Index: 443

Text #7

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1259. Min Act: -0.0001

Data Index: 411807 (C4 (Web Text))

Max Activating Token Index: 503

Text #8

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1328. Min Act: -0.0001

Data Index: 1161227 (C4 (Web Text))

Max Activating Token Index: 484

Text #9

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1250. Min Act: -0.0001

Data Index: 880288 (C4 (Web Text))

Max Activating Token Index: 51

Text #10

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1197. Min Act: -0.0001

Data Index: 824092 (C4 (Web Text))

Max Activating Token Index: 242

Text #11

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1231. Min Act: -0.0001

Data Index: 517898 (C4 (Web Text))

Max Activating Token Index: 139

Text #12

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1133. Min Act: -0.0001

Data Index: 759225 (C4 (Web Text))

Max Activating Token Index: 320

Text #13

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1213. Min Act: -0.0001

Data Index: 906701 (C4 (Web Text))

Max Activating Token Index: 507

Text #14

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1165. Min Act: -0.0001

Data Index: 1289596 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1210. Min Act: -0.0001

Data Index: 1328321 (C4 (Web Text))

Max Activating Token Index: 844

Text #16

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1168. Min Act: -0.0001

Data Index: 655869 (C4 (Web Text))

Max Activating Token Index: 48

Text #17

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1167. Min Act: -0.0001

Data Index: 699122 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1149. Min Act: -0.0001

Data Index: 1162832 (C4 (Web Text))

Max Activating Token Index: 258

Text #19

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1183. Min Act: -0.0001

Data Index: 356957 (C4 (Web Text))

Max Activating Token Index: 371