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

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

Neuron 108 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0266. Min Act: -0.0006

Data Index: 688165 (C4 (Web Text))

Max Activating Token Index: 88

Text #1

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0248. Min Act: -0.0006

Data Index: 1018107 (C4 (Web Text))

Max Activating Token Index: 300

Text #2

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0239. Min Act: -0.0006

Data Index: 1200789 (C4 (Web Text))

Max Activating Token Index: 330

Text #3

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0240. Min Act: -0.0006

Data Index: 657815 (C4 (Web Text))

Max Activating Token Index: 26

Text #4

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0238. Min Act: -0.0006

Data Index: 1273130 (C4 (Web Text))

Max Activating Token Index: 854

Text #5

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0236. Min Act: -0.0006

Data Index: 666543 (C4 (Web Text))

Max Activating Token Index: 855

Text #6

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0235. Min Act: -0.0006

Data Index: 1336224 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0229. Min Act: -0.0005

Data Index: 551407 (C4 (Web Text))

Max Activating Token Index: 820

Text #8

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0233. Min Act: -0.0006

Data Index: 108492 (C4 (Web Text))

Max Activating Token Index: 892

Text #9

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0231. Min Act: -0.0006

Data Index: 1220691 (C4 (Web Text))

Max Activating Token Index: 381

Text #10

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0235. Min Act: -0.0006

Data Index: 276960 (C4 (Web Text))

Max Activating Token Index: 909

Text #11

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0226. Min Act: -0.0006

Data Index: 942046 (C4 (Web Text))

Max Activating Token Index: 697

Text #12

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0226. Min Act: -0.0006

Data Index: 383467 (C4 (Web Text))

Max Activating Token Index: 334

Text #13

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0224. Min Act: -0.0006

Data Index: 606783 (C4 (Web Text))

Max Activating Token Index: 165

Text #14

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0218. Min Act: -0.0006

Data Index: 480843 (C4 (Web Text))

Max Activating Token Index: 796

Text #15

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0218. Min Act: -0.0006

Data Index: 1053670 (C4 (Web Text))

Max Activating Token Index: 844

Text #16

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0217. Min Act: -0.0006

Data Index: 674227 (C4 (Web Text))

Max Activating Token Index: 861

Text #17

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0221. Min Act: -0.0007

Data Index: 1288673 (C4 (Web Text))

Max Activating Token Index: 78

Text #18

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0216. Min Act: -0.0006

Data Index: 722881 (C4 (Web Text))

Max Activating Token Index: 612

Text #19

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0216. Min Act: -0.0006

Data Index: 607723 (C4 (Web Text))

Max Activating Token Index: 683