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

Dataset: The Pile

Neuron 2906 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0854. Min Range: -5.0854

Max Act: 4.8485. Min Act: -0.0000

Data Index: 1898432 (The Pile)

Max Activating Token Index: 792

Text #1

Max Range: 5.0854. Min Range: -5.0854

Max Act: 4.9174. Min Act: -0.0000

Data Index: 1309698 (The Pile)

Max Activating Token Index: 995

Text #2

Max Range: 5.0854. Min Range: -5.0854

Max Act: 5.0657. Min Act: -0.0000

Data Index: 70380 (The Pile)

Max Activating Token Index: 406

Text #3

Max Range: 5.0854. Min Range: -5.0854

Max Act: 5.0854. Min Act: -0.0000

Data Index: 60620 (The Pile)

Max Activating Token Index: 779

Text #4

Max Range: 5.0854. Min Range: -5.0854

Max Act: 4.2887. Min Act: -0.0000

Data Index: 517214 (The Pile)

Max Activating Token Index: 412

Text #5

Max Range: 5.0854. Min Range: -5.0854

Max Act: 4.2861. Min Act: -0.0000

Data Index: 79338 (The Pile)

Max Activating Token Index: 923

Text #6

Max Range: 5.0854. Min Range: -5.0854

Max Act: 4.1687. Min Act: -0.0000

Data Index: 1761183 (The Pile)

Max Activating Token Index: 371

Text #7

Max Range: 5.0854. Min Range: -5.0854

Max Act: 4.2819. Min Act: -0.0000

Data Index: 1203380 (The Pile)

Max Activating Token Index: 150

Text #8

Max Range: 5.0854. Min Range: -5.0854

Max Act: 4.5815. Min Act: -0.0000

Data Index: 1622423 (The Pile)

Max Activating Token Index: 584

Text #9

Max Range: 5.0854. Min Range: -5.0854

Max Act: 3.9801. Min Act: -0.0000

Data Index: 751138 (The Pile)

Max Activating Token Index: 473

Text #10

Max Range: 5.0854. Min Range: -5.0854

Max Act: 4.1047. Min Act: -0.0000

Data Index: 1667226 (The Pile)

Max Activating Token Index: 473

Text #11

Max Range: 5.0854. Min Range: -5.0854

Max Act: 4.0414. Min Act: -0.0000

Data Index: 740012 (The Pile)

Max Activating Token Index: 315

Text #12

Max Range: 5.0854. Min Range: -5.0854

Max Act: 4.3200. Min Act: -0.0000

Data Index: 1724797 (The Pile)

Max Activating Token Index: 624

Text #13

Max Range: 5.0854. Min Range: -5.0854

Max Act: 3.5794. Min Act: -0.0000

Data Index: 1377137 (The Pile)

Max Activating Token Index: 810

Text #14

Max Range: 5.0854. Min Range: -5.0854

Max Act: 3.2925. Min Act: -0.0000

Data Index: 278413 (The Pile)

Max Activating Token Index: 884

Text #15

Max Range: 5.0854. Min Range: -5.0854

Max Act: 3.6979. Min Act: -0.0000

Data Index: 222325 (The Pile)

Max Activating Token Index: 500

Text #16

Max Range: 5.0854. Min Range: -5.0854

Max Act: 3.7289. Min Act: -0.0000

Data Index: 1943157 (The Pile)

Max Activating Token Index: 41

Text #17

Max Range: 5.0854. Min Range: -5.0854

Max Act: 3.8624. Min Act: -0.0000

Data Index: 610740 (The Pile)

Max Activating Token Index: 53

Text #18

Max Range: 5.0854. Min Range: -5.0854

Max Act: 3.5472. Min Act: -0.0000

Data Index: 682086 (The Pile)

Max Activating Token Index: 725

Text #19

Max Range: 5.0854. Min Range: -5.0854

Max Act: 3.8375. Min Act: -0.0000

Data Index: 1806113 (The Pile)

Max Activating Token Index: 472