Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4570 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 6.8446. Min Range: -6.8446

Max Act: 6.7719. Min Act: -0.0000

Data Index: 160839 (C4 (Web Text))

Max Activating Token Index: 134

Text #1

Max Range: 6.8446. Min Range: -6.8446

Max Act: 6.6849. Min Act: -0.0000

Data Index: 7589 (C4 (Web Text))

Max Activating Token Index: 200

Text #2

Max Range: 6.8446. Min Range: -6.8446

Max Act: 6.8446. Min Act: -0.0000

Data Index: 201229 (C4 (Web Text))

Max Activating Token Index: 129

Text #3

Max Range: 6.8446. Min Range: -6.8446

Max Act: 6.0434. Min Act: -0.0000

Data Index: 227805 (C4 (Web Text))

Max Activating Token Index: 166

Text #4

Max Range: 6.8446. Min Range: -6.8446

Max Act: 5.8755. Min Act: -0.0000

Data Index: 802207 (C4 (Web Text))

Max Activating Token Index: 63

Text #5

Max Range: 6.8446. Min Range: -6.8446

Max Act: 5.8403. Min Act: -0.0000

Data Index: 619670 (C4 (Web Text))

Max Activating Token Index: 637

Text #6

Max Range: 6.8446. Min Range: -6.8446

Max Act: 5.8393. Min Act: -0.0000

Data Index: 805146 (C4 (Web Text))

Max Activating Token Index: 261

Text #7

Max Range: 6.8446. Min Range: -6.8446

Max Act: 5.5038. Min Act: -0.0000

Data Index: 266267 (C4 (Web Text))

Max Activating Token Index: 382

Text #8

Max Range: 6.8446. Min Range: -6.8446

Max Act: 5.5021. Min Act: -0.0000

Data Index: 913966 (C4 (Web Text))

Max Activating Token Index: 152

Text #9

Max Range: 6.8446. Min Range: -6.8446

Max Act: 5.5131. Min Act: -0.0000

Data Index: 397761 (C4 (Web Text))

Max Activating Token Index: 382

Text #10

Max Range: 6.8446. Min Range: -6.8446

Max Act: 5.6499. Min Act: -0.0000

Data Index: 1209882 (C4 (Web Text))

Max Activating Token Index: 118

Text #11

Max Range: 6.8446. Min Range: -6.8446

Max Act: 5.6034. Min Act: -0.0000

Data Index: 1321933 (C4 (Web Text))

Max Activating Token Index: 528

Text #12

Max Range: 6.8446. Min Range: -6.8446

Max Act: 5.4251. Min Act: -0.0000

Data Index: 290799 (C4 (Web Text))

Max Activating Token Index: 339

Text #13

Max Range: 6.8446. Min Range: -6.8446

Max Act: 5.6037. Min Act: -0.0000

Data Index: 1281807 (C4 (Web Text))

Max Activating Token Index: 188

Text #14

Max Range: 6.8446. Min Range: -6.8446

Max Act: 5.4204. Min Act: -0.0000

Data Index: 25494 (C4 (Web Text))

Max Activating Token Index: 893

Text #15

Max Range: 6.8446. Min Range: -6.8446

Max Act: 5.5454. Min Act: -0.0000

Data Index: 666157 (C4 (Web Text))

Max Activating Token Index: 295

Text #16

Max Range: 6.8446. Min Range: -6.8446

Max Act: 5.5243. Min Act: -0.0000

Data Index: 690272 (C4 (Web Text))

Max Activating Token Index: 288

Text #17

Max Range: 6.8446. Min Range: -6.8446

Max Act: 5.3561. Min Act: -0.0000

Data Index: 911657 (C4 (Web Text))

Max Activating Token Index: 182

Text #18

Max Range: 6.8446. Min Range: -6.8446

Max Act: 5.3558. Min Act: -0.0000

Data Index: 143559 (C4 (Web Text))

Max Activating Token Index: 536

Text #19

Max Range: 6.8446. Min Range: -6.8446

Max Act: 5.5317. Min Act: -0.0000

Data Index: 347132 (C4 (Web Text))

Max Activating Token Index: 301