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

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

Neuron 2792 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9185. Min Range: -0.9185

Max Act: 0.9162. Min Act: -0.0000

Data Index: 1329534 (C4 (Web Text))

Max Activating Token Index: 1009

Text #1

Max Range: 0.9185. Min Range: -0.9185

Max Act: 0.9185. Min Act: -0.0000

Data Index: 1258594 (C4 (Web Text))

Max Activating Token Index: 946

Text #2

Max Range: 0.9185. Min Range: -0.9185

Max Act: 0.9074. Min Act: -0.0000

Data Index: 835816 (C4 (Web Text))

Max Activating Token Index: 286

Text #3

Max Range: 0.9185. Min Range: -0.9185

Max Act: 0.8223. Min Act: -0.0000

Data Index: 544220 (C4 (Web Text))

Max Activating Token Index: 205

Text #4

Max Range: 0.9185. Min Range: -0.9185

Max Act: 0.8657. Min Act: -0.0000

Data Index: 381560 (C4 (Web Text))

Max Activating Token Index: 271

Text #5

Max Range: 0.9185. Min Range: -0.9185

Max Act: 0.8018. Min Act: -0.0000

Data Index: 131422 (C4 (Web Text))

Max Activating Token Index: 728

Text #6

Max Range: 0.9185. Min Range: -0.9185

Max Act: 0.7948. Min Act: -0.0000

Data Index: 325355 (C4 (Web Text))

Max Activating Token Index: 455

Text #7

Max Range: 0.9185. Min Range: -0.9185

Max Act: 0.7410. Min Act: -0.0000

Data Index: 668436 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 0.9185. Min Range: -0.9185

Max Act: 0.7836. Min Act: -0.0000

Data Index: 465167 (C4 (Web Text))

Max Activating Token Index: 610

Text #9

Max Range: 0.9185. Min Range: -0.9185

Max Act: 0.7335. Min Act: -0.0000

Data Index: 960509 (C4 (Web Text))

Max Activating Token Index: 970

Text #10

Max Range: 0.9185. Min Range: -0.9185

Max Act: 0.7530. Min Act: -0.0000

Data Index: 699473 (C4 (Web Text))

Max Activating Token Index: 620

Text #11

Max Range: 0.9185. Min Range: -0.9185

Max Act: 0.7465. Min Act: -0.0000

Data Index: 38174 (C4 (Web Text))

Max Activating Token Index: 264

Text #12

Max Range: 0.9185. Min Range: -0.9185

Max Act: 0.7259. Min Act: -0.0000

Data Index: 300855 (C4 (Web Text))

Max Activating Token Index: 915

Text #13

Max Range: 0.9185. Min Range: -0.9185

Max Act: 0.7292. Min Act: -0.0000

Data Index: 963435 (C4 (Web Text))

Max Activating Token Index: 130

Text #14

Max Range: 0.9185. Min Range: -0.9185

Max Act: 0.7289. Min Act: -0.0000

Data Index: 57678 (C4 (Web Text))

Max Activating Token Index: 193

Text #15

Max Range: 0.9185. Min Range: -0.9185

Max Act: 0.7208. Min Act: -0.0000

Data Index: 962110 (C4 (Web Text))

Max Activating Token Index: 1016

Text #16

Max Range: 0.9185. Min Range: -0.9185

Max Act: 0.7394. Min Act: -0.0000

Data Index: 1329815 (C4 (Web Text))

Max Activating Token Index: 983

Text #17

Max Range: 0.9185. Min Range: -0.9185

Max Act: 0.7367. Min Act: -0.0000

Data Index: 1166276 (C4 (Web Text))

Max Activating Token Index: 768

Text #18

Max Range: 0.9185. Min Range: -0.9185

Max Act: 0.6279. Min Act: 0.0000

Data Index: 315252 (C4 (Web Text))

Max Activating Token Index: 107

Text #19

Max Range: 0.9185. Min Range: -0.9185

Max Act: 0.6775. Min Act: -0.0000

Data Index: 222128 (C4 (Web Text))

Max Activating Token Index: 661