Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 555 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0330. Min Act: -0.0001

Data Index: 965439 (C4 (Web Text))

Max Activating Token Index: 671

Text #1

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0336. Min Act: -0.0001

Data Index: 334381 (C4 (Web Text))

Max Activating Token Index: 257

Text #2

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0326. Min Act: -0.0001

Data Index: 1021929 (C4 (Web Text))

Max Activating Token Index: 642

Text #3

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0323. Min Act: -0.0001

Data Index: 1292195 (C4 (Web Text))

Max Activating Token Index: 807

Text #4

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0306. Min Act: -0.0000

Data Index: 1099784 (C4 (Web Text))

Max Activating Token Index: 206

Text #5

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0323. Min Act: -0.0001

Data Index: 608815 (C4 (Web Text))

Max Activating Token Index: 846

Text #6

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0311. Min Act: -0.0001

Data Index: 1000299 (C4 (Web Text))

Max Activating Token Index: 947

Text #7

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0297. Min Act: -0.0001

Data Index: 1348817 (C4 (Web Text))

Max Activating Token Index: 678

Text #8

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0298. Min Act: -0.0000

Data Index: 552230 (C4 (Web Text))

Max Activating Token Index: 476

Text #9

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0292. Min Act: -0.0001

Data Index: 30305 (C4 (Web Text))

Max Activating Token Index: 724

Text #10

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0277. Min Act: -0.0000

Data Index: 97737 (C4 (Web Text))

Max Activating Token Index: 726

Text #11

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0248. Min Act: -0.0001

Data Index: 1239 (C4 (Web Text))

Max Activating Token Index: 375

Text #12

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0307. Min Act: -0.0001

Data Index: 893826 (C4 (Web Text))

Max Activating Token Index: 980

Text #13

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0274. Min Act: -0.0001

Data Index: 1328379 (C4 (Web Text))

Max Activating Token Index: 297

Text #14

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0285. Min Act: -0.0001

Data Index: 1004590 (C4 (Web Text))

Max Activating Token Index: 929

Text #15

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0271. Min Act: -0.0001

Data Index: 967366 (C4 (Web Text))

Max Activating Token Index: 188

Text #16

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0279. Min Act: -0.0001

Data Index: 121972 (C4 (Web Text))

Max Activating Token Index: 919

Text #17

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0290. Min Act: -0.0001

Data Index: 974297 (C4 (Web Text))

Max Activating Token Index: 265

Text #18

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0281. Min Act: -0.0001

Data Index: 1183138 (C4 (Web Text))

Max Activating Token Index: 443

Text #19

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0281. Min Act: -0.0001

Data Index: 752353 (C4 (Web Text))

Max Activating Token Index: 462