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

Dataset: The Pile

Neuron 498 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: 0.8744. Min Range: -0.8744

Max Act: 0.8744. Min Act: -0.0000

Data Index: 1482091 (The Pile)

Max Activating Token Index: 815

Text #1

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.8192. Min Act: -0.0000

Data Index: 143431 (The Pile)

Max Activating Token Index: 700

Text #2

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.7329. Min Act: -0.0000

Data Index: 660589 (The Pile)

Max Activating Token Index: 546

Text #3

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.7367. Min Act: -0.0000

Data Index: 1171026 (The Pile)

Max Activating Token Index: 917

Text #4

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.7371. Min Act: -0.0000

Data Index: 1427367 (The Pile)

Max Activating Token Index: 674

Text #5

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.7593. Min Act: -0.0000

Data Index: 1693300 (The Pile)

Max Activating Token Index: 862

Text #6

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.7064. Min Act: -0.0000

Data Index: 229235 (The Pile)

Max Activating Token Index: 691

Text #7

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.6629. Min Act: -0.0000

Data Index: 928309 (The Pile)

Max Activating Token Index: 205

Text #8

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.7208. Min Act: -0.0000

Data Index: 818153 (The Pile)

Max Activating Token Index: 178

Text #9

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.6671. Min Act: -0.0000

Data Index: 499081 (The Pile)

Max Activating Token Index: 180

Text #10

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.6854. Min Act: -0.0000

Data Index: 1299605 (The Pile)

Max Activating Token Index: 81

Text #11

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.6524. Min Act: -0.0000

Data Index: 1558159 (The Pile)

Max Activating Token Index: 174

Text #12

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.5713. Min Act: -0.0000

Data Index: 451882 (The Pile)

Max Activating Token Index: 688

Text #13

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.5964. Min Act: -0.0000

Data Index: 566920 (The Pile)

Max Activating Token Index: 563

Text #14

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.6083. Min Act: -0.0000

Data Index: 550990 (The Pile)

Max Activating Token Index: 484

Text #15

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.6019. Min Act: -0.0000

Data Index: 454582 (The Pile)

Max Activating Token Index: 345

Text #16

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.5398. Min Act: -0.0000

Data Index: 774140 (The Pile)

Max Activating Token Index: 877

Text #17

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.6046. Min Act: -0.0000

Data Index: 1191114 (The Pile)

Max Activating Token Index: 304

Text #18

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.5506. Min Act: -0.0000

Data Index: 514845 (The Pile)

Max Activating Token Index: 810

Text #19

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.5645. Min Act: -0.0000

Data Index: 1046582 (The Pile)

Max Activating Token Index: 442