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

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

Neuron 4256 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1390. Min Act: -0.0001

Data Index: 337832 (C4 (Web Text))

Max Activating Token Index: 51

Text #1

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1346. Min Act: -0.0001

Data Index: 147913 (C4 (Web Text))

Max Activating Token Index: 593

Text #2

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1370. Min Act: -0.0001

Data Index: 69234 (C4 (Web Text))

Max Activating Token Index: 442

Text #3

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1346. Min Act: -0.0001

Data Index: 694129 (C4 (Web Text))

Max Activating Token Index: 261

Text #4

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1315. Min Act: -0.0001

Data Index: 807752 (C4 (Web Text))

Max Activating Token Index: 118

Text #5

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1280. Min Act: -0.0001

Data Index: 985940 (C4 (Web Text))

Max Activating Token Index: 322

Text #6

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1245. Min Act: -0.0001

Data Index: 950225 (C4 (Web Text))

Max Activating Token Index: 98

Text #7

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1339. Min Act: -0.0001

Data Index: 1230567 (C4 (Web Text))

Max Activating Token Index: 8

Text #8

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1209. Min Act: -0.0001

Data Index: 326791 (C4 (Web Text))

Max Activating Token Index: 142

Text #9

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1234. Min Act: -0.0001

Data Index: 1036883 (C4 (Web Text))

Max Activating Token Index: 695

Text #10

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1141. Min Act: -0.0001

Data Index: 585740 (C4 (Web Text))

Max Activating Token Index: 879

Text #11

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1206. Min Act: -0.0001

Data Index: 1239555 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1159. Min Act: -0.0001

Data Index: 564010 (C4 (Web Text))

Max Activating Token Index: 891

Text #13

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1194. Min Act: -0.0001

Data Index: 689849 (C4 (Web Text))

Max Activating Token Index: 788

Text #14

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1185. Min Act: -0.0001

Data Index: 365604 (C4 (Web Text))

Max Activating Token Index: 127

Text #15

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1221. Min Act: -0.0001

Data Index: 1255445 (C4 (Web Text))

Max Activating Token Index: 17

Text #16

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1209. Min Act: -0.0001

Data Index: 196802 (C4 (Web Text))

Max Activating Token Index: 634

Text #17

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1182. Min Act: -0.0001

Data Index: 285465 (C4 (Web Text))

Max Activating Token Index: 495

Text #18

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1105. Min Act: -0.0001

Data Index: 492328 (C4 (Web Text))

Max Activating Token Index: 644

Text #19

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1262. Min Act: -0.0001

Data Index: 946221 (C4 (Web Text))

Max Activating Token Index: 380