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

Dataset: The Pile

Neuron 2020 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: 0.5846. Min Range: -0.5846

Max Act: 0.5618. Min Act: -0.0000

Data Index: 94874 (The Pile)

Max Activating Token Index: 996

Text #1

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.5846. Min Act: -0.0000

Data Index: 1983731 (The Pile)

Max Activating Token Index: 568

Text #2

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.5510. Min Act: -0.0000

Data Index: 375504 (The Pile)

Max Activating Token Index: 40

Text #3

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.4977. Min Act: -0.0000

Data Index: 1876847 (The Pile)

Max Activating Token Index: 28

Text #4

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.5067. Min Act: -0.0000

Data Index: 847497 (The Pile)

Max Activating Token Index: 113

Text #5

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.5151. Min Act: -0.0000

Data Index: 129932 (The Pile)

Max Activating Token Index: 100

Text #6

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.4527. Min Act: -0.0000

Data Index: 1009581 (The Pile)

Max Activating Token Index: 1015

Text #7

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.4683. Min Act: -0.0000

Data Index: 1738080 (The Pile)

Max Activating Token Index: 542

Text #8

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.4306. Min Act: -0.0000

Data Index: 483761 (The Pile)

Max Activating Token Index: 534

Text #9

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.4233. Min Act: -0.0000

Data Index: 263111 (The Pile)

Max Activating Token Index: 492

Text #10

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.4396. Min Act: -0.0000

Data Index: 1813047 (The Pile)

Max Activating Token Index: 845

Text #11

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.3786. Min Act: -0.0000

Data Index: 732139 (The Pile)

Max Activating Token Index: 1022

Text #12

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.4112. Min Act: -0.0000

Data Index: 1618361 (The Pile)

Max Activating Token Index: 747

Text #13

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.3411. Min Act: -0.0000

Data Index: 1010917 (The Pile)

Max Activating Token Index: 1021

Text #14

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.4054. Min Act: -0.0000

Data Index: 1543425 (The Pile)

Max Activating Token Index: 797

Text #15

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.3769. Min Act: -0.0000

Data Index: 1590374 (The Pile)

Max Activating Token Index: 540

Text #16

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.3319. Min Act: -0.0000

Data Index: 1926936 (The Pile)

Max Activating Token Index: 235

Text #17

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.3747. Min Act: -0.0000

Data Index: 1352439 (The Pile)

Max Activating Token Index: 415

Text #18

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.3645. Min Act: -0.0000

Data Index: 95068 (The Pile)

Max Activating Token Index: 295

Text #19

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.4024. Min Act: -0.0000

Data Index: 348420 (The Pile)

Max Activating Token Index: 765