Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 538 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0290. Min Act: -0.0006

Data Index: 213221 (C4 (Web Text))

Max Activating Token Index: 394

Text #1

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0277. Min Act: -0.0006

Data Index: 641790 (C4 (Web Text))

Max Activating Token Index: 894

Text #2

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0286. Min Act: -0.0006

Data Index: 303633 (C4 (Web Text))

Max Activating Token Index: 873

Text #3

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0279. Min Act: -0.0006

Data Index: 1239250 (C4 (Web Text))

Max Activating Token Index: 619

Text #4

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0265. Min Act: -0.0006

Data Index: 773925 (C4 (Web Text))

Max Activating Token Index: 154

Text #5

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0276. Min Act: -0.0005

Data Index: 1129678 (C4 (Web Text))

Max Activating Token Index: 501

Text #6

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0260. Min Act: -0.0006

Data Index: 735897 (C4 (Web Text))

Max Activating Token Index: 256

Text #7

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0258. Min Act: -0.0006

Data Index: 993006 (C4 (Web Text))

Max Activating Token Index: 923

Text #8

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0253. Min Act: -0.0006

Data Index: 177678 (C4 (Web Text))

Max Activating Token Index: 329

Text #9

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0246. Min Act: -0.0006

Data Index: 995781 (C4 (Web Text))

Max Activating Token Index: 804

Text #10

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0243. Min Act: -0.0006

Data Index: 1074401 (C4 (Web Text))

Max Activating Token Index: 291

Text #11

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0247. Min Act: -0.0006

Data Index: 451358 (C4 (Web Text))

Max Activating Token Index: 20

Text #12

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0248. Min Act: -0.0006

Data Index: 277971 (C4 (Web Text))

Max Activating Token Index: 183

Text #13

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0235. Min Act: -0.0006

Data Index: 823632 (C4 (Web Text))

Max Activating Token Index: 331

Text #14

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0244. Min Act: -0.0006

Data Index: 321710 (C4 (Web Text))

Max Activating Token Index: 619

Text #15

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0233. Min Act: -0.0006

Data Index: 1346755 (C4 (Web Text))

Max Activating Token Index: 909

Text #16

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0248. Min Act: -0.0006

Data Index: 34919 (C4 (Web Text))

Max Activating Token Index: 286

Text #17

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0238. Min Act: -0.0006

Data Index: 903582 (C4 (Web Text))

Max Activating Token Index: 112

Text #18

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0242. Min Act: -0.0006

Data Index: 369814 (C4 (Web Text))

Max Activating Token Index: 196

Text #19

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0235. Min Act: -0.0006

Data Index: 732994 (C4 (Web Text))

Max Activating Token Index: 925