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

Dataset: The Pile

Neuron 4640 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: 5.8416. Min Range: -5.8416

Max Act: 5.8416. Min Act: -0.0000

Data Index: 1716966 (The Pile)

Max Activating Token Index: 1018

Text #1

Max Range: 5.8416. Min Range: -5.8416

Max Act: 4.6875. Min Act: -0.0000

Data Index: 1762177 (The Pile)

Max Activating Token Index: 73

Text #2

Max Range: 5.8416. Min Range: -5.8416

Max Act: 3.6883. Min Act: -0.0000

Data Index: 1618314 (The Pile)

Max Activating Token Index: 312

Text #3

Max Range: 5.8416. Min Range: -5.8416

Max Act: 3.6921. Min Act: 0.0000

Data Index: 3451 (The Pile)

Max Activating Token Index: 176

Text #4

Max Range: 5.8416. Min Range: -5.8416

Max Act: 3.2337. Min Act: -0.0000

Data Index: 1548778 (The Pile)

Max Activating Token Index: 986

Text #5

Max Range: 5.8416. Min Range: -5.8416

Max Act: 3.5398. Min Act: -0.0000

Data Index: 806058 (The Pile)

Max Activating Token Index: 56

Text #6

Max Range: 5.8416. Min Range: -5.8416

Max Act: 3.8713. Min Act: -0.0000

Data Index: 1980522 (The Pile)

Max Activating Token Index: 264

Text #7

Max Range: 5.8416. Min Range: -5.8416

Max Act: 3.3897. Min Act: -0.0000

Data Index: 117824 (The Pile)

Max Activating Token Index: 990

Text #8

Max Range: 5.8416. Min Range: -5.8416

Max Act: 3.2189. Min Act: -0.0000

Data Index: 445642 (The Pile)

Max Activating Token Index: 516

Text #9

Max Range: 5.8416. Min Range: -5.8416

Max Act: 3.2203. Min Act: -0.0000

Data Index: 1204083 (The Pile)

Max Activating Token Index: 915

Text #10

Max Range: 5.8416. Min Range: -5.8416

Max Act: 3.0241. Min Act: -0.0000

Data Index: 1023918 (The Pile)

Max Activating Token Index: 327

Text #11

Max Range: 5.8416. Min Range: -5.8416

Max Act: 3.1639. Min Act: -0.0000

Data Index: 387618 (The Pile)

Max Activating Token Index: 173

Text #12

Max Range: 5.8416. Min Range: -5.8416

Max Act: 3.2777. Min Act: -0.0000

Data Index: 463775 (The Pile)

Max Activating Token Index: 277

Text #13

Max Range: 5.8416. Min Range: -5.8416

Max Act: 3.0609. Min Act: 0.0000

Data Index: 833503 (The Pile)

Max Activating Token Index: 954

Text #14

Max Range: 5.8416. Min Range: -5.8416

Max Act: 3.0519. Min Act: 0.0000

Data Index: 902235 (The Pile)

Max Activating Token Index: 247

Text #15

Max Range: 5.8416. Min Range: -5.8416

Max Act: 3.3188. Min Act: 0.0000

Data Index: 1981593 (The Pile)

Max Activating Token Index: 139

Text #16

Max Range: 5.8416. Min Range: -5.8416

Max Act: 3.0170. Min Act: -0.0000

Data Index: 702028 (The Pile)

Max Activating Token Index: 291

Text #17

Max Range: 5.8416. Min Range: -5.8416

Max Act: 3.2905. Min Act: -0.0000

Data Index: 145873 (The Pile)

Max Activating Token Index: 640

Text #18

Max Range: 5.8416. Min Range: -5.8416

Max Act: 3.1443. Min Act: -0.0000

Data Index: 292055 (The Pile)

Max Activating Token Index: 684

Text #19

Max Range: 5.8416. Min Range: -5.8416

Max Act: 3.2459. Min Act: -0.0000

Data Index: 1740563 (The Pile)

Max Activating Token Index: 880