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

Dataset: The Pile

Neuron 4626 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9124. Min Range: -0.9124

Max Act: 0.8998. Min Act: -0.0000

Data Index: 867720 (The Pile)

Max Activating Token Index: 686

Text #1

Max Range: 0.9124. Min Range: -0.9124

Max Act: 0.9124. Min Act: -0.0000

Data Index: 1656895 (The Pile)

Max Activating Token Index: 177

Text #2

Max Range: 0.9124. Min Range: -0.9124

Max Act: 0.8197. Min Act: -0.0000

Data Index: 1178911 (The Pile)

Max Activating Token Index: 314

Text #3

Max Range: 0.9124. Min Range: -0.9124

Max Act: 0.8350. Min Act: 0.0000

Data Index: 267645 (The Pile)

Max Activating Token Index: 27

Text #4

Max Range: 0.9124. Min Range: -0.9124

Max Act: 0.8280. Min Act: -0.0000

Data Index: 58036 (The Pile)

Max Activating Token Index: 83

Text #5

Max Range: 0.9124. Min Range: -0.9124

Max Act: 0.7903. Min Act: -0.0000

Data Index: 902658 (The Pile)

Max Activating Token Index: 332

Text #6

Max Range: 0.9124. Min Range: -0.9124

Max Act: 0.7789. Min Act: -0.0000

Data Index: 1898686 (The Pile)

Max Activating Token Index: 24

Text #7

Max Range: 0.9124. Min Range: -0.9124

Max Act: 0.7953. Min Act: -0.0000

Data Index: 446714 (The Pile)

Max Activating Token Index: 261

Text #8

Max Range: 0.9124. Min Range: -0.9124

Max Act: 0.7195. Min Act: -0.0000

Data Index: 20765 (The Pile)

Max Activating Token Index: 912

Text #9

Max Range: 0.9124. Min Range: -0.9124

Max Act: 0.6496. Min Act: -0.0000

Data Index: 14032 (The Pile)

Max Activating Token Index: 979

Text #10

Max Range: 0.9124. Min Range: -0.9124

Max Act: 0.7219. Min Act: -0.0000

Data Index: 1919203 (The Pile)

Max Activating Token Index: 484

Text #11

Max Range: 0.9124. Min Range: -0.9124

Max Act: 0.7485. Min Act: -0.0000

Data Index: 1519472 (The Pile)

Max Activating Token Index: 569

Text #12

Max Range: 0.9124. Min Range: -0.9124

Max Act: 0.7593. Min Act: -0.0000

Data Index: 1101104 (The Pile)

Max Activating Token Index: 515

Text #13

Max Range: 0.9124. Min Range: -0.9124

Max Act: 0.7395. Min Act: -0.0000

Data Index: 1766915 (The Pile)

Max Activating Token Index: 755

Text #14

Max Range: 0.9124. Min Range: -0.9124

Max Act: 0.6548. Min Act: -0.0000

Data Index: 1163674 (The Pile)

Max Activating Token Index: 248

Text #15

Max Range: 0.9124. Min Range: -0.9124

Max Act: 0.6975. Min Act: -0.0000

Data Index: 683504 (The Pile)

Max Activating Token Index: 321

Text #16

Max Range: 0.9124. Min Range: -0.9124

Max Act: 0.6740. Min Act: -0.0000

Data Index: 888988 (The Pile)

Max Activating Token Index: 357

Text #17

Max Range: 0.9124. Min Range: -0.9124

Max Act: 0.6731. Min Act: -0.0000

Data Index: 464983 (The Pile)

Max Activating Token Index: 285

Text #18

Max Range: 0.9124. Min Range: -0.9124

Max Act: 0.7170. Min Act: -0.0000

Data Index: 672272 (The Pile)

Max Activating Token Index: 633

Text #19

Max Range: 0.9124. Min Range: -0.9124

Max Act: 0.7165. Min Act: -0.0000

Data Index: 1704633 (The Pile)

Max Activating Token Index: 601