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

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

Neuron 498 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.1421. Min Act: -0.0005

Data Index: 758887 (C4 (Web Text))

Max Activating Token Index: 841

Text #1

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.1310. Min Act: -0.0005

Data Index: 839194 (C4 (Web Text))

Max Activating Token Index: 1022

Text #2

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.1341. Min Act: -0.0005

Data Index: 987454 (C4 (Web Text))

Max Activating Token Index: 375

Text #3

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.1309. Min Act: -0.0005

Data Index: 275155 (C4 (Web Text))

Max Activating Token Index: 39

Text #4

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.1353. Min Act: -0.0005

Data Index: 147287 (C4 (Web Text))

Max Activating Token Index: 567

Text #5

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.1274. Min Act: -0.0005

Data Index: 83802 (C4 (Web Text))

Max Activating Token Index: 289

Text #6

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.1281. Min Act: -0.0005

Data Index: 573674 (C4 (Web Text))

Max Activating Token Index: 724

Text #7

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.1319. Min Act: -0.0005

Data Index: 61560 (C4 (Web Text))

Max Activating Token Index: 784

Text #8

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.1357. Min Act: -0.0005

Data Index: 608457 (C4 (Web Text))

Max Activating Token Index: 312

Text #9

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.1226. Min Act: -0.0005

Data Index: 1150666 (C4 (Web Text))

Max Activating Token Index: 695

Text #10

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.1259. Min Act: -0.0005

Data Index: 1249112 (C4 (Web Text))

Max Activating Token Index: 356

Text #11

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.1247. Min Act: -0.0005

Data Index: 517363 (C4 (Web Text))

Max Activating Token Index: 792

Text #12

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.1283. Min Act: -0.0005

Data Index: 114076 (C4 (Web Text))

Max Activating Token Index: 435

Text #13

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.1206. Min Act: -0.0005

Data Index: 980670 (C4 (Web Text))

Max Activating Token Index: 78

Text #14

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.1263. Min Act: -0.0005

Data Index: 178605 (C4 (Web Text))

Max Activating Token Index: 833

Text #15

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.1106. Min Act: -0.0005

Data Index: 1257301 (C4 (Web Text))

Max Activating Token Index: 514

Text #16

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.1142. Min Act: -0.0005

Data Index: 1098164 (C4 (Web Text))

Max Activating Token Index: 92

Text #17

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.1294. Min Act: -0.0005

Data Index: 832754 (C4 (Web Text))

Max Activating Token Index: 479

Text #18

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.1159. Min Act: -0.0005

Data Index: 694994 (C4 (Web Text))

Max Activating Token Index: 79

Text #19

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.1163. Min Act: -0.0005

Data Index: 1156983 (C4 (Web Text))

Max Activating Token Index: 537