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

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

Neuron 1605 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1466. Min Act: -0.0002

Data Index: 117543 (C4 (Web Text))

Max Activating Token Index: 333

Text #1

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1386. Min Act: -0.0002

Data Index: 730160 (C4 (Web Text))

Max Activating Token Index: 552

Text #2

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1363. Min Act: -0.0002

Data Index: 401609 (C4 (Web Text))

Max Activating Token Index: 499

Text #3

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1360. Min Act: -0.0001

Data Index: 458609 (C4 (Web Text))

Max Activating Token Index: 213

Text #4

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1369. Min Act: -0.0001

Data Index: 671597 (C4 (Web Text))

Max Activating Token Index: 683

Text #5

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1338. Min Act: -0.0002

Data Index: 712185 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1313. Min Act: -0.0002

Data Index: 259521 (C4 (Web Text))

Max Activating Token Index: 75

Text #7

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1276. Min Act: -0.0002

Data Index: 1079093 (C4 (Web Text))

Max Activating Token Index: 36

Text #8

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1289. Min Act: -0.0002

Data Index: 1028403 (C4 (Web Text))

Max Activating Token Index: 410

Text #9

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1281. Min Act: -0.0002

Data Index: 638050 (C4 (Web Text))

Max Activating Token Index: 73

Text #10

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1270. Min Act: -0.0002

Data Index: 887261 (C4 (Web Text))

Max Activating Token Index: 573

Text #11

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1226. Min Act: -0.0001

Data Index: 1046241 (C4 (Web Text))

Max Activating Token Index: 70

Text #12

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1235. Min Act: -0.0002

Data Index: 803959 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1195. Min Act: -0.0002

Data Index: 431090 (C4 (Web Text))

Max Activating Token Index: 633

Text #14

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1178. Min Act: -0.0002

Data Index: 281677 (C4 (Web Text))

Max Activating Token Index: 812

Text #15

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1214. Min Act: -0.0002

Data Index: 544036 (C4 (Web Text))

Max Activating Token Index: 1014

Text #16

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1222. Min Act: -0.0002

Data Index: 1295968 (C4 (Web Text))

Max Activating Token Index: 519

Text #17

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1181. Min Act: -0.0002

Data Index: 625171 (C4 (Web Text))

Max Activating Token Index: 369

Text #18

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1177. Min Act: -0.0002

Data Index: 738941 (C4 (Web Text))

Max Activating Token Index: 857

Text #19

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1128. Min Act: -0.0002

Data Index: 522512 (C4 (Web Text))

Max Activating Token Index: 735