Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2244 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1373. Min Act: -0.0003

Data Index: 949659 (C4 (Web Text))

Max Activating Token Index: 423

Text #1

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1309. Min Act: -0.0003

Data Index: 27405 (C4 (Web Text))

Max Activating Token Index: 402

Text #2

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1280. Min Act: -0.0003

Data Index: 537935 (C4 (Web Text))

Max Activating Token Index: 469

Text #3

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1270. Min Act: -0.0003

Data Index: 1243266 (C4 (Web Text))

Max Activating Token Index: 394

Text #4

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1288. Min Act: -0.0003

Data Index: 355068 (C4 (Web Text))

Max Activating Token Index: 383

Text #5

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1227. Min Act: -0.0003

Data Index: 1061172 (C4 (Web Text))

Max Activating Token Index: 545

Text #6

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1194. Min Act: -0.0003

Data Index: 666307 (C4 (Web Text))

Max Activating Token Index: 444

Text #7

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1232. Min Act: -0.0003

Data Index: 812056 (C4 (Web Text))

Max Activating Token Index: 373

Text #8

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1224. Min Act: -0.0003

Data Index: 982382 (C4 (Web Text))

Max Activating Token Index: 576

Text #9

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1242. Min Act: -0.0003

Data Index: 359444 (C4 (Web Text))

Max Activating Token Index: 474

Text #10

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1200. Min Act: -0.0003

Data Index: 1285659 (C4 (Web Text))

Max Activating Token Index: 448

Text #11

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1171. Min Act: -0.0003

Data Index: 918350 (C4 (Web Text))

Max Activating Token Index: 382

Text #12

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1150. Min Act: -0.0003

Data Index: 107270 (C4 (Web Text))

Max Activating Token Index: 332

Text #13

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1188. Min Act: -0.0003

Data Index: 710843 (C4 (Web Text))

Max Activating Token Index: 389

Text #14

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1238. Min Act: -0.0003

Data Index: 1351378 (C4 (Web Text))

Max Activating Token Index: 403

Text #15

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1165. Min Act: -0.0003

Data Index: 466186 (C4 (Web Text))

Max Activating Token Index: 408

Text #16

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1141. Min Act: -0.0003

Data Index: 662597 (C4 (Web Text))

Max Activating Token Index: 318

Text #17

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1209. Min Act: -0.0003

Data Index: 221568 (C4 (Web Text))

Max Activating Token Index: 477

Text #18

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1164. Min Act: -0.0003

Data Index: 200938 (C4 (Web Text))

Max Activating Token Index: 525

Text #19

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1153. Min Act: -0.0003

Data Index: 663807 (C4 (Web Text))

Max Activating Token Index: 466