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

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

Neuron 2031 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: 0.1462. Min Range: -0.1462

Max Act: 0.1462. Min Act: -0.0002

Data Index: 126588 (C4 (Web Text))

Max Activating Token Index: 266

Text #1

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1382. Min Act: -0.0002

Data Index: 971636 (C4 (Web Text))

Max Activating Token Index: 910

Text #2

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1296. Min Act: -0.0002

Data Index: 372405 (C4 (Web Text))

Max Activating Token Index: 567

Text #3

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1296. Min Act: -0.0002

Data Index: 631223 (C4 (Web Text))

Max Activating Token Index: 279

Text #4

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1338. Min Act: -0.0002

Data Index: 1273244 (C4 (Web Text))

Max Activating Token Index: 942

Text #5

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1235. Min Act: -0.0002

Data Index: 728485 (C4 (Web Text))

Max Activating Token Index: 963

Text #6

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1306. Min Act: -0.0002

Data Index: 1256534 (C4 (Web Text))

Max Activating Token Index: 470

Text #7

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1163. Min Act: -0.0002

Data Index: 680702 (C4 (Web Text))

Max Activating Token Index: 832

Text #8

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1225. Min Act: -0.0002

Data Index: 103022 (C4 (Web Text))

Max Activating Token Index: 593

Text #9

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1259. Min Act: -0.0002

Data Index: 37597 (C4 (Web Text))

Max Activating Token Index: 966

Text #10

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1238. Min Act: -0.0002

Data Index: 943840 (C4 (Web Text))

Max Activating Token Index: 707

Text #11

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1187. Min Act: -0.0002

Data Index: 841049 (C4 (Web Text))

Max Activating Token Index: 315

Text #12

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1189. Min Act: -0.0002

Data Index: 898406 (C4 (Web Text))

Max Activating Token Index: 343

Text #13

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1264. Min Act: -0.0002

Data Index: 13609 (C4 (Web Text))

Max Activating Token Index: 161

Text #14

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1230. Min Act: -0.0002

Data Index: 853571 (C4 (Web Text))

Max Activating Token Index: 842

Text #15

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1228. Min Act: -0.0001

Data Index: 920683 (C4 (Web Text))

Max Activating Token Index: 135

Text #16

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1217. Min Act: -0.0001

Data Index: 676272 (C4 (Web Text))

Max Activating Token Index: 23

Text #17

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1142. Min Act: -0.0002

Data Index: 519947 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1239. Min Act: -0.0002

Data Index: 1023365 (C4 (Web Text))

Max Activating Token Index: 347

Text #19

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1197. Min Act: -0.0002

Data Index: 1210909 (C4 (Web Text))

Max Activating Token Index: 908