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

Dataset: The Pile

Neuron 2218 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6878. Min Range: -1.6878

Max Act: 1.6878. Min Act: -0.0000

Data Index: 138319 (The Pile)

Max Activating Token Index: 544

Text #1

Max Range: 1.6878. Min Range: -1.6878

Max Act: 1.4794. Min Act: -0.0000

Data Index: 815996 (The Pile)

Max Activating Token Index: 89

Text #2

Max Range: 1.6878. Min Range: -1.6878

Max Act: 1.5565. Min Act: -0.0000

Data Index: 517711 (The Pile)

Max Activating Token Index: 223

Text #3

Max Range: 1.6878. Min Range: -1.6878

Max Act: 1.5207. Min Act: -0.0000

Data Index: 934927 (The Pile)

Max Activating Token Index: 447

Text #4

Max Range: 1.6878. Min Range: -1.6878

Max Act: 1.4777. Min Act: -0.0000

Data Index: 1542429 (The Pile)

Max Activating Token Index: 590

Text #5

Max Range: 1.6878. Min Range: -1.6878

Max Act: 1.5687. Min Act: -0.0000

Data Index: 436534 (The Pile)

Max Activating Token Index: 299

Text #6

Max Range: 1.6878. Min Range: -1.6878

Max Act: 1.5686. Min Act: -0.0000

Data Index: 672829 (The Pile)

Max Activating Token Index: 300

Text #7

Max Range: 1.6878. Min Range: -1.6878

Max Act: 1.4647. Min Act: -0.0000

Data Index: 357375 (The Pile)

Max Activating Token Index: 743

Text #8

Max Range: 1.6878. Min Range: -1.6878

Max Act: 1.5166. Min Act: -0.0000

Data Index: 130826 (The Pile)

Max Activating Token Index: 567

Text #9

Max Range: 1.6878. Min Range: -1.6878

Max Act: 1.4177. Min Act: -0.0000

Data Index: 95721 (The Pile)

Max Activating Token Index: 342

Text #10

Max Range: 1.6878. Min Range: -1.6878

Max Act: 1.3928. Min Act: -0.0000

Data Index: 490512 (The Pile)

Max Activating Token Index: 886

Text #11

Max Range: 1.6878. Min Range: -1.6878

Max Act: 1.3956. Min Act: -0.0000

Data Index: 919664 (The Pile)

Max Activating Token Index: 566

Text #12

Max Range: 1.6878. Min Range: -1.6878

Max Act: 1.3462. Min Act: 0.0000

Data Index: 1273955 (The Pile)

Max Activating Token Index: 415

Text #13

Max Range: 1.6878. Min Range: -1.6878

Max Act: 1.3382. Min Act: -0.0000

Data Index: 1014483 (The Pile)

Max Activating Token Index: 529

Text #14

Max Range: 1.6878. Min Range: -1.6878

Max Act: 1.3428. Min Act: -0.0000

Data Index: 1303506 (The Pile)

Max Activating Token Index: 299

Text #15

Max Range: 1.6878. Min Range: -1.6878

Max Act: 1.3444. Min Act: -0.0000

Data Index: 559283 (The Pile)

Max Activating Token Index: 362

Text #16

Max Range: 1.6878. Min Range: -1.6878

Max Act: 1.2344. Min Act: -0.0000

Data Index: 1683698 (The Pile)

Max Activating Token Index: 765

Text #17

Max Range: 1.6878. Min Range: -1.6878

Max Act: 1.3014. Min Act: -0.0000

Data Index: 698393 (The Pile)

Max Activating Token Index: 415

Text #18

Max Range: 1.6878. Min Range: -1.6878

Max Act: 1.3750. Min Act: -0.0000

Data Index: 1740288 (The Pile)

Max Activating Token Index: 773

Text #19

Max Range: 1.6878. Min Range: -1.6878

Max Act: 1.2874. Min Act: -0.0000

Data Index: 484213 (The Pile)

Max Activating Token Index: 412