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

Dataset: The Pile

Neuron 4140 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: 1.4594. Min Range: -1.4594

Max Act: 1.4594. Min Act: -0.0000

Data Index: 388380 (The Pile)

Max Activating Token Index: 264

Text #1

Max Range: 1.4594. Min Range: -1.4594

Max Act: 1.4236. Min Act: -0.0000

Data Index: 301570 (The Pile)

Max Activating Token Index: 580

Text #2

Max Range: 1.4594. Min Range: -1.4594

Max Act: 1.3022. Min Act: -0.0000

Data Index: 1695409 (The Pile)

Max Activating Token Index: 356

Text #3

Max Range: 1.4594. Min Range: -1.4594

Max Act: 1.2628. Min Act: -0.0000

Data Index: 654065 (The Pile)

Max Activating Token Index: 739

Text #4

Max Range: 1.4594. Min Range: -1.4594

Max Act: 1.2711. Min Act: -0.0000

Data Index: 483574 (The Pile)

Max Activating Token Index: 452

Text #5

Max Range: 1.4594. Min Range: -1.4594

Max Act: 1.2305. Min Act: -0.0000

Data Index: 1717548 (The Pile)

Max Activating Token Index: 180

Text #6

Max Range: 1.4594. Min Range: -1.4594

Max Act: 1.3143. Min Act: -0.0000

Data Index: 1127048 (The Pile)

Max Activating Token Index: 416

Text #7

Max Range: 1.4594. Min Range: -1.4594

Max Act: 1.2935. Min Act: -0.0000

Data Index: 1034676 (The Pile)

Max Activating Token Index: 560

Text #8

Max Range: 1.4594. Min Range: -1.4594

Max Act: 1.2280. Min Act: -0.0000

Data Index: 290607 (The Pile)

Max Activating Token Index: 419

Text #9

Max Range: 1.4594. Min Range: -1.4594

Max Act: 1.2901. Min Act: -0.0000

Data Index: 1599954 (The Pile)

Max Activating Token Index: 792

Text #10

Max Range: 1.4594. Min Range: -1.4594

Max Act: 1.2873. Min Act: -0.0000

Data Index: 1175344 (The Pile)

Max Activating Token Index: 970

Text #11

Max Range: 1.4594. Min Range: -1.4594

Max Act: 1.3695. Min Act: -0.0000

Data Index: 446560 (The Pile)

Max Activating Token Index: 978

Text #12

Max Range: 1.4594. Min Range: -1.4594

Max Act: 1.3535. Min Act: -0.0000

Data Index: 535920 (The Pile)

Max Activating Token Index: 608

Text #13

Max Range: 1.4594. Min Range: -1.4594

Max Act: 1.2610. Min Act: -0.0000

Data Index: 1293496 (The Pile)

Max Activating Token Index: 363

Text #14

Max Range: 1.4594. Min Range: -1.4594

Max Act: 1.1749. Min Act: -0.0000

Data Index: 1063942 (The Pile)

Max Activating Token Index: 857

Text #15

Max Range: 1.4594. Min Range: -1.4594

Max Act: 1.2384. Min Act: -0.0000

Data Index: 34552 (The Pile)

Max Activating Token Index: 839

Text #16

Max Range: 1.4594. Min Range: -1.4594

Max Act: 1.3229. Min Act: -0.0000

Data Index: 571126 (The Pile)

Max Activating Token Index: 458

Text #17

Max Range: 1.4594. Min Range: -1.4594

Max Act: 1.1608. Min Act: -0.0000

Data Index: 285353 (The Pile)

Max Activating Token Index: 580

Text #18

Max Range: 1.4594. Min Range: -1.4594

Max Act: 1.1362. Min Act: -0.0000

Data Index: 233747 (The Pile)

Max Activating Token Index: 423

Text #19

Max Range: 1.4594. Min Range: -1.4594

Max Act: 1.2107. Min Act: -0.0000

Data Index: 733999 (The Pile)

Max Activating Token Index: 84