Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5967 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1244. Min Act: -0.0002

Data Index: 276553 (C4 (Web Text))

Max Activating Token Index: 450

Text #1

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1271. Min Act: -0.0002

Data Index: 560736 (C4 (Web Text))

Max Activating Token Index: 243

Text #2

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1274. Min Act: -0.0002

Data Index: 191505 (C4 (Web Text))

Max Activating Token Index: 559

Text #3

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1380. Min Act: -0.0002

Data Index: 1075948 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1297. Min Act: -0.0002

Data Index: 242303 (C4 (Web Text))

Max Activating Token Index: 655

Text #5

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1216. Min Act: -0.0002

Data Index: 859125 (C4 (Web Text))

Max Activating Token Index: 211

Text #6

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1233. Min Act: -0.0002

Data Index: 526397 (C4 (Web Text))

Max Activating Token Index: 704

Text #7

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1327. Min Act: -0.0002

Data Index: 47999 (C4 (Web Text))

Max Activating Token Index: 819

Text #8

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1147. Min Act: -0.0002

Data Index: 1071995 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1241. Min Act: -0.0002

Data Index: 529165 (C4 (Web Text))

Max Activating Token Index: 490

Text #10

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1241. Min Act: -0.0002

Data Index: 1097768 (C4 (Web Text))

Max Activating Token Index: 420

Text #11

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1130. Min Act: -0.0002

Data Index: 211399 (C4 (Web Text))

Max Activating Token Index: 722

Text #12

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1133. Min Act: -0.0002

Data Index: 207110 (C4 (Web Text))

Max Activating Token Index: 236

Text #13

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1184. Min Act: -0.0002

Data Index: 1271879 (C4 (Web Text))

Max Activating Token Index: 957

Text #14

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1267. Min Act: -0.0002

Data Index: 896275 (C4 (Web Text))

Max Activating Token Index: 441

Text #15

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1258. Min Act: -0.0002

Data Index: 1149970 (C4 (Web Text))

Max Activating Token Index: 654

Text #16

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1145. Min Act: -0.0002

Data Index: 340519 (C4 (Web Text))

Max Activating Token Index: 803

Text #17

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.0958. Min Act: -0.0002

Data Index: 1128602 (C4 (Web Text))

Max Activating Token Index: 310

Text #18

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1169. Min Act: -0.0002

Data Index: 1162534 (C4 (Web Text))

Max Activating Token Index: 386

Text #19

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1302. Min Act: -0.0002

Data Index: 476997 (C4 (Web Text))

Max Activating Token Index: 659