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

Dataset: The Pile

Neuron 4200 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0382. Min Act: -0.0000

Data Index: 882457 (The Pile)

Max Activating Token Index: 444

Text #1

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0292. Min Act: -0.0000

Data Index: 1993123 (The Pile)

Max Activating Token Index: 736

Text #2

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0286. Min Act: -0.0000

Data Index: 867986 (The Pile)

Max Activating Token Index: 198

Text #3

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0286. Min Act: -0.0000

Data Index: 160311 (The Pile)

Max Activating Token Index: 505

Text #4

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0285. Min Act: -0.0000

Data Index: 733953 (The Pile)

Max Activating Token Index: 233

Text #5

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0282. Min Act: -0.0000

Data Index: 337352 (The Pile)

Max Activating Token Index: 490

Text #6

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0279. Min Act: -0.0000

Data Index: 825676 (The Pile)

Max Activating Token Index: 960

Text #7

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0277. Min Act: -0.0000

Data Index: 1482411 (The Pile)

Max Activating Token Index: 43

Text #8

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0265. Min Act: -0.0000

Data Index: 251244 (The Pile)

Max Activating Token Index: 101

Text #9

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0263. Min Act: -0.0000

Data Index: 1293281 (The Pile)

Max Activating Token Index: 115

Text #10

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0274. Min Act: -0.0000

Data Index: 1474049 (The Pile)

Max Activating Token Index: 191

Text #11

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0269. Min Act: -0.0000

Data Index: 1896609 (The Pile)

Max Activating Token Index: 88

Text #12

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0267. Min Act: -0.0000

Data Index: 870064 (The Pile)

Max Activating Token Index: 111

Text #13

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0267. Min Act: -0.0000

Data Index: 1084217 (The Pile)

Max Activating Token Index: 704

Text #14

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0272. Min Act: -0.0000

Data Index: 1733277 (The Pile)

Max Activating Token Index: 993

Text #15

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0261. Min Act: -0.0000

Data Index: 1496827 (The Pile)

Max Activating Token Index: 231

Text #16

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0260. Min Act: -0.0000

Data Index: 1786517 (The Pile)

Max Activating Token Index: 211

Text #17

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0259. Min Act: -0.0000

Data Index: 833637 (The Pile)

Max Activating Token Index: 436

Text #18

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0258. Min Act: -0.0000

Data Index: 1013328 (The Pile)

Max Activating Token Index: 139

Text #19

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0258. Min Act: -0.0000

Data Index: 323346 (The Pile)

Max Activating Token Index: 672