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

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

Neuron 2774 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0263. Min Act: -0.0003

Data Index: 1073740 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0266. Min Act: -0.0003

Data Index: 994453 (C4 (Web Text))

Max Activating Token Index: 738

Text #2

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0255. Min Act: -0.0004

Data Index: 695588 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0255. Min Act: -0.0003

Data Index: 278548 (C4 (Web Text))

Max Activating Token Index: 665

Text #4

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0254. Min Act: -0.0003

Data Index: 739018 (C4 (Web Text))

Max Activating Token Index: 127

Text #5

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0249. Min Act: -0.0003

Data Index: 258066 (C4 (Web Text))

Max Activating Token Index: 640

Text #6

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0242. Min Act: -0.0004

Data Index: 893632 (C4 (Web Text))

Max Activating Token Index: 262

Text #7

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0230. Min Act: -0.0003

Data Index: 1292633 (C4 (Web Text))

Max Activating Token Index: 502

Text #8

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0235. Min Act: -0.0004

Data Index: 781247 (C4 (Web Text))

Max Activating Token Index: 97

Text #9

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0232. Min Act: -0.0003

Data Index: 595294 (C4 (Web Text))

Max Activating Token Index: 549

Text #10

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0232. Min Act: -0.0004

Data Index: 1052360 (C4 (Web Text))

Max Activating Token Index: 172

Text #11

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0228. Min Act: -0.0003

Data Index: 744012 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0231. Min Act: -0.0004

Data Index: 370837 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0231. Min Act: -0.0003

Data Index: 963573 (C4 (Web Text))

Max Activating Token Index: 558

Text #14

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0226. Min Act: -0.0003

Data Index: 1244396 (C4 (Web Text))

Max Activating Token Index: 345

Text #15

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0229. Min Act: -0.0004

Data Index: 836338 (C4 (Web Text))

Max Activating Token Index: 756

Text #16

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0228. Min Act: -0.0003

Data Index: 455629 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0227. Min Act: -0.0004

Data Index: 740247 (C4 (Web Text))

Max Activating Token Index: 137

Text #18

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0227. Min Act: -0.0004

Data Index: 191305 (C4 (Web Text))

Max Activating Token Index: 921

Text #19

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0225. Min Act: -0.0003

Data Index: 855822 (C4 (Web Text))

Max Activating Token Index: 902