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

Dataset: The Pile

Neuron 4108 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3711. Min Range: -0.3711

Max Act: 0.3614. Min Act: -0.0000

Data Index: 1434953 (The Pile)

Max Activating Token Index: 995

Text #1

Max Range: 0.3711. Min Range: -0.3711

Max Act: 0.3711. Min Act: -0.0001

Data Index: 251334 (The Pile)

Max Activating Token Index: 576

Text #2

Max Range: 0.3711. Min Range: -0.3711

Max Act: 0.3392. Min Act: -0.0000

Data Index: 830184 (The Pile)

Max Activating Token Index: 296

Text #3

Max Range: 0.3711. Min Range: -0.3711

Max Act: 0.3406. Min Act: -0.0000

Data Index: 78264 (The Pile)

Max Activating Token Index: 749

Text #4

Max Range: 0.3711. Min Range: -0.3711

Max Act: 0.3266. Min Act: -0.0000

Data Index: 1814658 (The Pile)

Max Activating Token Index: 508

Text #5

Max Range: 0.3711. Min Range: -0.3711

Max Act: 0.3099. Min Act: -0.0000

Data Index: 1776143 (The Pile)

Max Activating Token Index: 608

Text #6

Max Range: 0.3711. Min Range: -0.3711

Max Act: 0.3254. Min Act: -0.0000

Data Index: 611526 (The Pile)

Max Activating Token Index: 281

Text #7

Max Range: 0.3711. Min Range: -0.3711

Max Act: 0.2507. Min Act: -0.0000

Data Index: 108931 (The Pile)

Max Activating Token Index: 915

Text #8

Max Range: 0.3711. Min Range: -0.3711

Max Act: 0.3244. Min Act: -0.0000

Data Index: 929998 (The Pile)

Max Activating Token Index: 279

Text #9

Max Range: 0.3711. Min Range: -0.3711

Max Act: 0.3026. Min Act: -0.0000

Data Index: 406155 (The Pile)

Max Activating Token Index: 929

Text #10

Max Range: 0.3711. Min Range: -0.3711

Max Act: 0.3369. Min Act: -0.0000

Data Index: 1411105 (The Pile)

Max Activating Token Index: 954

Text #11

Max Range: 0.3711. Min Range: -0.3711

Max Act: 0.2977. Min Act: -0.0000

Data Index: 310716 (The Pile)

Max Activating Token Index: 478

Text #12

Max Range: 0.3711. Min Range: -0.3711

Max Act: 0.3082. Min Act: -0.0000

Data Index: 1626766 (The Pile)

Max Activating Token Index: 366

Text #13

Max Range: 0.3711. Min Range: -0.3711

Max Act: 0.2888. Min Act: -0.0000

Data Index: 1571603 (The Pile)

Max Activating Token Index: 791

Text #14

Max Range: 0.3711. Min Range: -0.3711

Max Act: 0.3110. Min Act: -0.0000

Data Index: 854275 (The Pile)

Max Activating Token Index: 920

Text #15

Max Range: 0.3711. Min Range: -0.3711

Max Act: 0.3116. Min Act: -0.0000

Data Index: 172273 (The Pile)

Max Activating Token Index: 683

Text #16

Max Range: 0.3711. Min Range: -0.3711

Max Act: 0.3136. Min Act: -0.0000

Data Index: 317878 (The Pile)

Max Activating Token Index: 998

Text #17

Max Range: 0.3711. Min Range: -0.3711

Max Act: 0.2875. Min Act: -0.0000

Data Index: 1660059 (The Pile)

Max Activating Token Index: 325

Text #18

Max Range: 0.3711. Min Range: -0.3711

Max Act: 0.2712. Min Act: -0.0000

Data Index: 1159008 (The Pile)

Max Activating Token Index: 849

Text #19

Max Range: 0.3711. Min Range: -0.3711

Max Act: 0.2967. Min Act: -0.0000

Data Index: 1928116 (The Pile)

Max Activating Token Index: 23