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

Dataset: The Pile

Neuron 327 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.4946. Min Act: -0.0000

Data Index: 1620664 (The Pile)

Max Activating Token Index: 144

Text #1

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.4298. Min Act: -0.0000

Data Index: 1260349 (The Pile)

Max Activating Token Index: 668

Text #2

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3997. Min Act: -0.0000

Data Index: 1889329 (The Pile)

Max Activating Token Index: 247

Text #3

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.4071. Min Act: -0.0000

Data Index: 1428512 (The Pile)

Max Activating Token Index: 58

Text #4

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3816. Min Act: -0.0000

Data Index: 107574 (The Pile)

Max Activating Token Index: 514

Text #5

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3655. Min Act: -0.0000

Data Index: 982752 (The Pile)

Max Activating Token Index: 61

Text #6

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3397. Min Act: -0.0000

Data Index: 1877197 (The Pile)

Max Activating Token Index: 832

Text #7

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3635. Min Act: -0.0000

Data Index: 1024402 (The Pile)

Max Activating Token Index: 44

Text #8

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3496. Min Act: -0.0000

Data Index: 1283980 (The Pile)

Max Activating Token Index: 170

Text #9

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3357. Min Act: -0.0000

Data Index: 965411 (The Pile)

Max Activating Token Index: 757

Text #10

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3535. Min Act: -0.0000

Data Index: 887116 (The Pile)

Max Activating Token Index: 943

Text #11

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3566. Min Act: 0.0000

Data Index: 394634 (The Pile)

Max Activating Token Index: 682

Text #12

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3378. Min Act: -0.0000

Data Index: 154672 (The Pile)

Max Activating Token Index: 282

Text #13

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3567. Min Act: -0.0000

Data Index: 1995824 (The Pile)

Max Activating Token Index: 736

Text #14

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3439. Min Act: -0.0000

Data Index: 1490036 (The Pile)

Max Activating Token Index: 806

Text #15

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3288. Min Act: -0.0000

Data Index: 693459 (The Pile)

Max Activating Token Index: 43

Text #16

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3165. Min Act: -0.0000

Data Index: 494629 (The Pile)

Max Activating Token Index: 961

Text #17

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3144. Min Act: -0.0000

Data Index: 1169154 (The Pile)

Max Activating Token Index: 44

Text #18

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3234. Min Act: -0.0000

Data Index: 423072 (The Pile)

Max Activating Token Index: 105

Text #19

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3252. Min Act: -0.0000

Data Index: 582066 (The Pile)

Max Activating Token Index: 139