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

Dataset: The Pile

Neuron 904 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: 1.2601. Min Range: -1.2601

Max Act: 1.2601. Min Act: -0.0000

Data Index: 1526042 (The Pile)

Max Activating Token Index: 966

Text #1

Max Range: 1.2601. Min Range: -1.2601

Max Act: 0.4221. Min Act: -0.0000

Data Index: 751479 (The Pile)

Max Activating Token Index: 933

Text #2

Max Range: 1.2601. Min Range: -1.2601

Max Act: 0.4821. Min Act: -0.0000

Data Index: 1202619 (The Pile)

Max Activating Token Index: 494

Text #3

Max Range: 1.2601. Min Range: -1.2601

Max Act: 0.4150. Min Act: -0.0000

Data Index: 1719494 (The Pile)

Max Activating Token Index: 399

Text #4

Max Range: 1.2601. Min Range: -1.2601

Max Act: 0.3671. Min Act: -0.0000

Data Index: 1463281 (The Pile)

Max Activating Token Index: 711

Text #5

Max Range: 1.2601. Min Range: -1.2601

Max Act: 0.3549. Min Act: -0.0000

Data Index: 801081 (The Pile)

Max Activating Token Index: 126

Text #6

Max Range: 1.2601. Min Range: -1.2601

Max Act: 0.3479. Min Act: -0.0000

Data Index: 1969660 (The Pile)

Max Activating Token Index: 497

Text #7

Max Range: 1.2601. Min Range: -1.2601

Max Act: 0.3406. Min Act: -0.0000

Data Index: 955136 (The Pile)

Max Activating Token Index: 973

Text #8

Max Range: 1.2601. Min Range: -1.2601

Max Act: 0.3176. Min Act: -0.0000

Data Index: 726807 (The Pile)

Max Activating Token Index: 936

Text #9

Max Range: 1.2601. Min Range: -1.2601

Max Act: 0.3317. Min Act: -0.0000

Data Index: 1685273 (The Pile)

Max Activating Token Index: 698

Text #10

Max Range: 1.2601. Min Range: -1.2601

Max Act: 0.3367. Min Act: -0.0000

Data Index: 491383 (The Pile)

Max Activating Token Index: 811

Text #11

Max Range: 1.2601. Min Range: -1.2601

Max Act: 0.3335. Min Act: -0.0000

Data Index: 448138 (The Pile)

Max Activating Token Index: 652

Text #12

Max Range: 1.2601. Min Range: -1.2601

Max Act: 0.3298. Min Act: -0.0000

Data Index: 1674729 (The Pile)

Max Activating Token Index: 896

Text #13

Max Range: 1.2601. Min Range: -1.2601

Max Act: 0.3404. Min Act: -0.0000

Data Index: 474089 (The Pile)

Max Activating Token Index: 671

Text #14

Max Range: 1.2601. Min Range: -1.2601

Max Act: 0.3057. Min Act: -0.0000

Data Index: 684808 (The Pile)

Max Activating Token Index: 605

Text #15

Max Range: 1.2601. Min Range: -1.2601

Max Act: 0.3002. Min Act: -0.0000

Data Index: 360664 (The Pile)

Max Activating Token Index: 44

Text #16

Max Range: 1.2601. Min Range: -1.2601

Max Act: 0.3226. Min Act: -0.0000

Data Index: 1281305 (The Pile)

Max Activating Token Index: 565

Text #17

Max Range: 1.2601. Min Range: -1.2601

Max Act: 0.3174. Min Act: -0.0000

Data Index: 1992286 (The Pile)

Max Activating Token Index: 299

Text #18

Max Range: 1.2601. Min Range: -1.2601

Max Act: 0.3185. Min Act: -0.0000

Data Index: 1651884 (The Pile)

Max Activating Token Index: 915

Text #19

Max Range: 1.2601. Min Range: -1.2601

Max Act: 0.2864. Min Act: -0.0000

Data Index: 757723 (The Pile)

Max Activating Token Index: 610