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

Dataset: The Pile

Neuron 1610 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: 0.3407. Min Range: -0.3407

Max Act: 0.3355. Min Act: -0.0000

Data Index: 1020684 (The Pile)

Max Activating Token Index: 430

Text #1

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.3301. Min Act: -0.0000

Data Index: 1238236 (The Pile)

Max Activating Token Index: 759

Text #2

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.3407. Min Act: -0.0000

Data Index: 1563608 (The Pile)

Max Activating Token Index: 97

Text #3

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.3217. Min Act: -0.0000

Data Index: 291264 (The Pile)

Max Activating Token Index: 508

Text #4

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.3327. Min Act: -0.0000

Data Index: 640045 (The Pile)

Max Activating Token Index: 146

Text #5

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.3176. Min Act: -0.0000

Data Index: 1051961 (The Pile)

Max Activating Token Index: 677

Text #6

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.3089. Min Act: -0.0000

Data Index: 1772883 (The Pile)

Max Activating Token Index: 27

Text #7

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.3326. Min Act: -0.0000

Data Index: 1471594 (The Pile)

Max Activating Token Index: 853

Text #8

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2980. Min Act: -0.0000

Data Index: 600860 (The Pile)

Max Activating Token Index: 255

Text #9

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2981. Min Act: -0.0000

Data Index: 1437605 (The Pile)

Max Activating Token Index: 108

Text #10

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2736. Min Act: -0.0000

Data Index: 1957355 (The Pile)

Max Activating Token Index: 859

Text #11

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2618. Min Act: -0.0000

Data Index: 1776024 (The Pile)

Max Activating Token Index: 721

Text #12

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2578. Min Act: -0.0000

Data Index: 16733 (The Pile)

Max Activating Token Index: 26

Text #13

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2463. Min Act: -0.0000

Data Index: 1005869 (The Pile)

Max Activating Token Index: 302

Text #14

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2450. Min Act: -0.0000

Data Index: 159464 (The Pile)

Max Activating Token Index: 89

Text #15

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2430. Min Act: -0.0000

Data Index: 879318 (The Pile)

Max Activating Token Index: 427

Text #16

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2337. Min Act: -0.0000

Data Index: 1545631 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2491. Min Act: -0.0000

Data Index: 453500 (The Pile)

Max Activating Token Index: 115

Text #18

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2470. Min Act: -0.0000

Data Index: 1031949 (The Pile)

Max Activating Token Index: 19

Text #19

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2358. Min Act: -0.0000

Data Index: 1314030 (The Pile)

Max Activating Token Index: 46