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

Dataset: The Pile

Neuron 674 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4172. Min Range: -0.4172

Max Act: 0.4172. Min Act: -0.0000

Data Index: 1348974 (The Pile)

Max Activating Token Index: 294

Text #1

Max Range: 0.4172. Min Range: -0.4172

Max Act: 0.3582. Min Act: -0.0000

Data Index: 59985 (The Pile)

Max Activating Token Index: 622

Text #2

Max Range: 0.4172. Min Range: -0.4172

Max Act: 0.3651. Min Act: -0.0000

Data Index: 987470 (The Pile)

Max Activating Token Index: 446

Text #3

Max Range: 0.4172. Min Range: -0.4172

Max Act: 0.3657. Min Act: -0.0000

Data Index: 1710517 (The Pile)

Max Activating Token Index: 352

Text #4

Max Range: 0.4172. Min Range: -0.4172

Max Act: 0.3487. Min Act: -0.0000

Data Index: 517479 (The Pile)

Max Activating Token Index: 146

Text #5

Max Range: 0.4172. Min Range: -0.4172

Max Act: 0.3474. Min Act: -0.0000

Data Index: 27190 (The Pile)

Max Activating Token Index: 477

Text #6

Max Range: 0.4172. Min Range: -0.4172

Max Act: 0.3307. Min Act: -0.0000

Data Index: 912789 (The Pile)

Max Activating Token Index: 449

Text #7

Max Range: 0.4172. Min Range: -0.4172

Max Act: 0.3545. Min Act: -0.0000

Data Index: 1941792 (The Pile)

Max Activating Token Index: 845

Text #8

Max Range: 0.4172. Min Range: -0.4172

Max Act: 0.3115. Min Act: -0.0000

Data Index: 362409 (The Pile)

Max Activating Token Index: 907

Text #9

Max Range: 0.4172. Min Range: -0.4172

Max Act: 0.3129. Min Act: -0.0000

Data Index: 684156 (The Pile)

Max Activating Token Index: 252

Text #10

Max Range: 0.4172. Min Range: -0.4172

Max Act: 0.2981. Min Act: -0.0000

Data Index: 1762622 (The Pile)

Max Activating Token Index: 66

Text #11

Max Range: 0.4172. Min Range: -0.4172

Max Act: 0.2696. Min Act: -0.0000

Data Index: 1001809 (The Pile)

Max Activating Token Index: 411

Text #12

Max Range: 0.4172. Min Range: -0.4172

Max Act: 0.3478. Min Act: -0.0000

Data Index: 1447024 (The Pile)

Max Activating Token Index: 705

Text #13

Max Range: 0.4172. Min Range: -0.4172

Max Act: 0.2819. Min Act: -0.0000

Data Index: 1869855 (The Pile)

Max Activating Token Index: 195

Text #14

Max Range: 0.4172. Min Range: -0.4172

Max Act: 0.2751. Min Act: -0.0000

Data Index: 44203 (The Pile)

Max Activating Token Index: 952

Text #15

Max Range: 0.4172. Min Range: -0.4172

Max Act: 0.2521. Min Act: -0.0000

Data Index: 1204894 (The Pile)

Max Activating Token Index: 438

Text #16

Max Range: 0.4172. Min Range: -0.4172

Max Act: 0.2623. Min Act: -0.0000

Data Index: 1549081 (The Pile)

Max Activating Token Index: 870

Text #17

Max Range: 0.4172. Min Range: -0.4172

Max Act: 0.2824. Min Act: -0.0000

Data Index: 897479 (The Pile)

Max Activating Token Index: 245

Text #18

Max Range: 0.4172. Min Range: -0.4172

Max Act: 0.2551. Min Act: -0.0000

Data Index: 1700421 (The Pile)

Max Activating Token Index: 199

Text #19

Max Range: 0.4172. Min Range: -0.4172

Max Act: 0.2461. Min Act: -0.0000

Data Index: 157504 (The Pile)

Max Activating Token Index: 474