Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2258 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1375. Min Act: -0.0001

Data Index: 1319661 (C4 (Web Text))

Max Activating Token Index: 287

Text #1

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1390. Min Act: -0.0001

Data Index: 373184 (C4 (Web Text))

Max Activating Token Index: 637

Text #2

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1407. Min Act: -0.0001

Data Index: 1268958 (C4 (Web Text))

Max Activating Token Index: 835

Text #3

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1391. Min Act: -0.0001

Data Index: 1058620 (C4 (Web Text))

Max Activating Token Index: 416

Text #4

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1323. Min Act: -0.0001

Data Index: 396564 (C4 (Web Text))

Max Activating Token Index: 483

Text #5

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1305. Min Act: -0.0001

Data Index: 1061643 (C4 (Web Text))

Max Activating Token Index: 247

Text #6

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1301. Min Act: -0.0001

Data Index: 149227 (C4 (Web Text))

Max Activating Token Index: 512

Text #7

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1232. Min Act: -0.0001

Data Index: 680927 (C4 (Web Text))

Max Activating Token Index: 497

Text #8

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1265. Min Act: -0.0001

Data Index: 89923 (C4 (Web Text))

Max Activating Token Index: 453

Text #9

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1246. Min Act: -0.0001

Data Index: 1012729 (C4 (Web Text))

Max Activating Token Index: 890

Text #10

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1237. Min Act: -0.0001

Data Index: 787691 (C4 (Web Text))

Max Activating Token Index: 861

Text #11

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1321. Min Act: -0.0001

Data Index: 1249213 (C4 (Web Text))

Max Activating Token Index: 693

Text #12

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1275. Min Act: -0.0001

Data Index: 379750 (C4 (Web Text))

Max Activating Token Index: 278

Text #13

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1262. Min Act: -0.0001

Data Index: 1349512 (C4 (Web Text))

Max Activating Token Index: 283

Text #14

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1247. Min Act: -0.0001

Data Index: 420517 (C4 (Web Text))

Max Activating Token Index: 399

Text #15

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1214. Min Act: -0.0001

Data Index: 995482 (C4 (Web Text))

Max Activating Token Index: 240

Text #16

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1248. Min Act: -0.0001

Data Index: 728949 (C4 (Web Text))

Max Activating Token Index: 288

Text #17

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1205. Min Act: -0.0001

Data Index: 133652 (C4 (Web Text))

Max Activating Token Index: 1022

Text #18

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1273. Min Act: -0.0001

Data Index: 1329586 (C4 (Web Text))

Max Activating Token Index: 615

Text #19

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1140. Min Act: -0.0001

Data Index: 365254 (C4 (Web Text))

Max Activating Token Index: 314