Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1533 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7971. Min Range: -0.7971

Max Act: 0.7971. Min Act: -0.0000

Data Index: 1343748 (The Pile)

Max Activating Token Index: 188

Text #1

Max Range: 0.7971. Min Range: -0.7971

Max Act: 0.7787. Min Act: -0.0000

Data Index: 708024 (The Pile)

Max Activating Token Index: 173

Text #2

Max Range: 0.7971. Min Range: -0.7971

Max Act: 0.7599. Min Act: -0.0000

Data Index: 1936835 (The Pile)

Max Activating Token Index: 500

Text #3

Max Range: 0.7971. Min Range: -0.7971

Max Act: 0.6698. Min Act: -0.0000

Data Index: 923650 (The Pile)

Max Activating Token Index: 586

Text #4

Max Range: 0.7971. Min Range: -0.7971

Max Act: 0.6925. Min Act: -0.0000

Data Index: 768696 (The Pile)

Max Activating Token Index: 392

Text #5

Max Range: 0.7971. Min Range: -0.7971

Max Act: 0.7231. Min Act: -0.0000

Data Index: 1084315 (The Pile)

Max Activating Token Index: 603

Text #6

Max Range: 0.7971. Min Range: -0.7971

Max Act: 0.5401. Min Act: -0.0000

Data Index: 1396696 (The Pile)

Max Activating Token Index: 966

Text #7

Max Range: 0.7971. Min Range: -0.7971

Max Act: 0.5710. Min Act: -0.0000

Data Index: 652964 (The Pile)

Max Activating Token Index: 435

Text #8

Max Range: 0.7971. Min Range: -0.7971

Max Act: 0.5711. Min Act: -0.0000

Data Index: 1951529 (The Pile)

Max Activating Token Index: 949

Text #9

Max Range: 0.7971. Min Range: -0.7971

Max Act: 0.5897. Min Act: -0.0000

Data Index: 203660 (The Pile)

Max Activating Token Index: 246

Text #10

Max Range: 0.7971. Min Range: -0.7971

Max Act: 0.5161. Min Act: -0.0000

Data Index: 100425 (The Pile)

Max Activating Token Index: 670

Text #11

Max Range: 0.7971. Min Range: -0.7971

Max Act: 0.3917. Min Act: -0.0000

Data Index: 1744369 (The Pile)

Max Activating Token Index: 59

Text #12

Max Range: 0.7971. Min Range: -0.7971

Max Act: 0.4448. Min Act: -0.0000

Data Index: 1306112 (The Pile)

Max Activating Token Index: 248

Text #13

Max Range: 0.7971. Min Range: -0.7971

Max Act: 0.4504. Min Act: -0.0000

Data Index: 300648 (The Pile)

Max Activating Token Index: 972

Text #14

Max Range: 0.7971. Min Range: -0.7971

Max Act: 0.4210. Min Act: -0.0000

Data Index: 201874 (The Pile)

Max Activating Token Index: 472

Text #15

Max Range: 0.7971. Min Range: -0.7971

Max Act: 0.3513. Min Act: -0.0000

Data Index: 818364 (The Pile)

Max Activating Token Index: 111

Text #16

Max Range: 0.7971. Min Range: -0.7971

Max Act: 0.3121. Min Act: -0.0000

Data Index: 857485 (The Pile)

Max Activating Token Index: 507

Text #17

Max Range: 0.7971. Min Range: -0.7971

Max Act: 0.3486. Min Act: -0.0000

Data Index: 615575 (The Pile)

Max Activating Token Index: 763

Text #18

Max Range: 0.7971. Min Range: -0.7971

Max Act: 0.3422. Min Act: -0.0000

Data Index: 1155401 (The Pile)

Max Activating Token Index: 303

Text #19

Max Range: 0.7971. Min Range: -0.7971

Max Act: 0.3291. Min Act: -0.0000

Data Index: 1801538 (The Pile)

Max Activating Token Index: 755