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

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

Neuron 623 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9124. Min Range: -2.9124

Max Act: 2.7888. Min Act: -0.0000

Data Index: 1652658 (Python Code)

Max Activating Token Index: 183

Text #1

Max Range: 2.9124. Min Range: -2.9124

Max Act: 2.9124. Min Act: -0.0000

Data Index: 1555566 (Python Code)

Max Activating Token Index: 505

Text #2

Max Range: 2.9124. Min Range: -2.9124

Max Act: 2.6717. Min Act: -0.0000

Data Index: 1544640 (Python Code)

Max Activating Token Index: 234

Text #3

Max Range: 2.9124. Min Range: -2.9124

Max Act: 2.6164. Min Act: -0.0000

Data Index: 1462764 (Python Code)

Max Activating Token Index: 51

Text #4

Max Range: 2.9124. Min Range: -2.9124

Max Act: 2.5578. Min Act: -0.0000

Data Index: 1512232 (Python Code)

Max Activating Token Index: 306

Text #5

Max Range: 2.9124. Min Range: -2.9124

Max Act: 2.4661. Min Act: -0.0000

Data Index: 1388015 (Python Code)

Max Activating Token Index: 225

Text #6

Max Range: 2.9124. Min Range: -2.9124

Max Act: 2.4894. Min Act: -0.0000

Data Index: 1458419 (Python Code)

Max Activating Token Index: 485

Text #7

Max Range: 2.9124. Min Range: -2.9124

Max Act: 2.4738. Min Act: -0.0000

Data Index: 1584321 (Python Code)

Max Activating Token Index: 290

Text #8

Max Range: 2.9124. Min Range: -2.9124

Max Act: 2.4277. Min Act: -0.0000

Data Index: 1639441 (Python Code)

Max Activating Token Index: 92

Text #9

Max Range: 2.9124. Min Range: -2.9124

Max Act: 2.4172. Min Act: -0.0000

Data Index: 1376003 (Python Code)

Max Activating Token Index: 451

Text #10

Max Range: 2.9124. Min Range: -2.9124

Max Act: 2.5153. Min Act: -0.0000

Data Index: 1488898 (Python Code)

Max Activating Token Index: 116

Text #11

Max Range: 2.9124. Min Range: -2.9124

Max Act: 2.3760. Min Act: -0.0000

Data Index: 1624648 (Python Code)

Max Activating Token Index: 209

Text #12

Max Range: 2.9124. Min Range: -2.9124

Max Act: 2.3420. Min Act: -0.0000

Data Index: 1528469 (Python Code)

Max Activating Token Index: 537

Text #13

Max Range: 2.9124. Min Range: -2.9124

Max Act: 2.3256. Min Act: -0.0000

Data Index: 1444880 (Python Code)

Max Activating Token Index: 7

Text #14

Max Range: 2.9124. Min Range: -2.9124

Max Act: 2.3156. Min Act: -0.0000

Data Index: 1571700 (Python Code)

Max Activating Token Index: 404

Text #15

Max Range: 2.9124. Min Range: -2.9124

Max Act: 2.3161. Min Act: -0.0000

Data Index: 1492755 (Python Code)

Max Activating Token Index: 234

Text #16

Max Range: 2.9124. Min Range: -2.9124

Max Act: 2.4028. Min Act: -0.0000

Data Index: 1571068 (Python Code)

Max Activating Token Index: 169

Text #17

Max Range: 2.9124. Min Range: -2.9124

Max Act: 2.2763. Min Act: -0.0000

Data Index: 1454595 (Python Code)

Max Activating Token Index: 202

Text #18

Max Range: 2.9124. Min Range: -2.9124

Max Act: 2.1440. Min Act: -0.0000

Data Index: 1601366 (Python Code)

Max Activating Token Index: 595

Text #19

Max Range: 2.9124. Min Range: -2.9124

Max Act: 2.2426. Min Act: -0.0000

Data Index: 1406326 (Python Code)

Max Activating Token Index: 599