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

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

Neuron 3157 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: 0.0527. Min Range: -0.0527

Max Act: 0.0527. Min Act: -0.0000

Data Index: 825594 (C4 (Web Text))

Max Activating Token Index: 118

Text #1

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0474. Min Act: -0.0000

Data Index: 141709 (C4 (Web Text))

Max Activating Token Index: 672

Text #2

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0488. Min Act: -0.0001

Data Index: 114849 (C4 (Web Text))

Max Activating Token Index: 131

Text #3

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0474. Min Act: -0.0001

Data Index: 595476 (C4 (Web Text))

Max Activating Token Index: 622

Text #4

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0511. Min Act: -0.0000

Data Index: 556515 (C4 (Web Text))

Max Activating Token Index: 877

Text #5

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0493. Min Act: -0.0001

Data Index: 18732 (C4 (Web Text))

Max Activating Token Index: 338

Text #6

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0429. Min Act: -0.0001

Data Index: 365779 (C4 (Web Text))

Max Activating Token Index: 292

Text #7

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0461. Min Act: -0.0001

Data Index: 507795 (C4 (Web Text))

Max Activating Token Index: 492

Text #8

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0414. Min Act: -0.0001

Data Index: 671589 (C4 (Web Text))

Max Activating Token Index: 250

Text #9

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0445. Min Act: -0.0000

Data Index: 664283 (C4 (Web Text))

Max Activating Token Index: 405

Text #10

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0434. Min Act: -0.0000

Data Index: 205260 (C4 (Web Text))

Max Activating Token Index: 194

Text #11

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0413. Min Act: -0.0001

Data Index: 1006004 (C4 (Web Text))

Max Activating Token Index: 181

Text #12

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0400. Min Act: -0.0000

Data Index: 202959 (C4 (Web Text))

Max Activating Token Index: 254

Text #13

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0426. Min Act: -0.0001

Data Index: 221531 (C4 (Web Text))

Max Activating Token Index: 623

Text #14

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0452. Min Act: -0.0001

Data Index: 1246805 (C4 (Web Text))

Max Activating Token Index: 644

Text #15

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0416. Min Act: -0.0001

Data Index: 615985 (C4 (Web Text))

Max Activating Token Index: 151

Text #16

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0405. Min Act: -0.0000

Data Index: 732687 (C4 (Web Text))

Max Activating Token Index: 249

Text #17

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0442. Min Act: -0.0001

Data Index: 543013 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0372. Min Act: -0.0000

Data Index: 1095876 (C4 (Web Text))

Max Activating Token Index: 851

Text #19

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0427. Min Act: -0.0000

Data Index: 562379 (C4 (Web Text))

Max Activating Token Index: 180