Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1446 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0268. Min Act: -0.0006

Data Index: 177387 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0259. Min Act: -0.0005

Data Index: 295080 (C4 (Web Text))

Max Activating Token Index: 218

Text #2

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0258. Min Act: -0.0005

Data Index: 737487 (C4 (Web Text))

Max Activating Token Index: 120

Text #3

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0256. Min Act: -0.0005

Data Index: 512919 (C4 (Web Text))

Max Activating Token Index: 734

Text #4

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0252. Min Act: -0.0005

Data Index: 780985 (C4 (Web Text))

Max Activating Token Index: 444

Text #5

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0246. Min Act: -0.0005

Data Index: 782630 (C4 (Web Text))

Max Activating Token Index: 265

Text #6

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0249. Min Act: -0.0005

Data Index: 638042 (C4 (Web Text))

Max Activating Token Index: 547

Text #7

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0243. Min Act: -0.0005

Data Index: 98337 (C4 (Web Text))

Max Activating Token Index: 262

Text #8

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0241. Min Act: -0.0006

Data Index: 999053 (C4 (Web Text))

Max Activating Token Index: 845

Text #9

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0241. Min Act: -0.0005

Data Index: 591818 (C4 (Web Text))

Max Activating Token Index: 323

Text #10

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0245. Min Act: -0.0005

Data Index: 357673 (C4 (Web Text))

Max Activating Token Index: 134

Text #11

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0239. Min Act: -0.0005

Data Index: 42301 (C4 (Web Text))

Max Activating Token Index: 149

Text #12

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0242. Min Act: -0.0006

Data Index: 275269 (C4 (Web Text))

Max Activating Token Index: 854

Text #13

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0237. Min Act: -0.0005

Data Index: 1115209 (C4 (Web Text))

Max Activating Token Index: 440

Text #14

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0237. Min Act: -0.0005

Data Index: 386428 (C4 (Web Text))

Max Activating Token Index: 683

Text #15

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0237. Min Act: -0.0005

Data Index: 27915 (C4 (Web Text))

Max Activating Token Index: 111

Text #16

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0242. Min Act: -0.0005

Data Index: 1143828 (C4 (Web Text))

Max Activating Token Index: 863

Text #17

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0231. Min Act: -0.0005

Data Index: 15180 (C4 (Web Text))

Max Activating Token Index: 824

Text #18

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0236. Min Act: -0.0005

Data Index: 1285709 (C4 (Web Text))

Max Activating Token Index: 86

Text #19

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0236. Min Act: -0.0005

Data Index: 724614 (C4 (Web Text))

Max Activating Token Index: 36