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

Dataset: The Pile

Neuron 2733 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: 1.0277. Min Range: -1.0277

Max Act: 1.0277. Min Act: -0.0000

Data Index: 715046 (The Pile)

Max Activating Token Index: 634

Text #1

Max Range: 1.0277. Min Range: -1.0277

Max Act: 0.9321. Min Act: -0.0000

Data Index: 1212219 (The Pile)

Max Activating Token Index: 944

Text #2

Max Range: 1.0277. Min Range: -1.0277

Max Act: 0.9315. Min Act: -0.0000

Data Index: 591915 (The Pile)

Max Activating Token Index: 503

Text #3

Max Range: 1.0277. Min Range: -1.0277

Max Act: 0.8341. Min Act: 0.0000

Data Index: 234468 (The Pile)

Max Activating Token Index: 940

Text #4

Max Range: 1.0277. Min Range: -1.0277

Max Act: 0.8015. Min Act: -0.0000

Data Index: 63778 (The Pile)

Max Activating Token Index: 511

Text #5

Max Range: 1.0277. Min Range: -1.0277

Max Act: 0.7566. Min Act: -0.0000

Data Index: 956614 (The Pile)

Max Activating Token Index: 428

Text #6

Max Range: 1.0277. Min Range: -1.0277

Max Act: 0.7506. Min Act: -0.0000

Data Index: 1933637 (The Pile)

Max Activating Token Index: 510

Text #7

Max Range: 1.0277. Min Range: -1.0277

Max Act: 0.7239. Min Act: -0.0000

Data Index: 381200 (The Pile)

Max Activating Token Index: 1000

Text #8

Max Range: 1.0277. Min Range: -1.0277

Max Act: 0.7224. Min Act: -0.0000

Data Index: 102125 (The Pile)

Max Activating Token Index: 953

Text #9

Max Range: 1.0277. Min Range: -1.0277

Max Act: 0.7505. Min Act: -0.0000

Data Index: 1970543 (The Pile)

Max Activating Token Index: 314

Text #10

Max Range: 1.0277. Min Range: -1.0277

Max Act: 0.7115. Min Act: -0.0000

Data Index: 1147933 (The Pile)

Max Activating Token Index: 305

Text #11

Max Range: 1.0277. Min Range: -1.0277

Max Act: 0.7768. Min Act: -0.0000

Data Index: 835700 (The Pile)

Max Activating Token Index: 559

Text #12

Max Range: 1.0277. Min Range: -1.0277

Max Act: 0.6745. Min Act: -0.0000

Data Index: 1729005 (The Pile)

Max Activating Token Index: 134

Text #13

Max Range: 1.0277. Min Range: -1.0277

Max Act: 0.6620. Min Act: -0.0000

Data Index: 1715195 (The Pile)

Max Activating Token Index: 643

Text #14

Max Range: 1.0277. Min Range: -1.0277

Max Act: 0.6946. Min Act: -0.0000

Data Index: 773560 (The Pile)

Max Activating Token Index: 386

Text #15

Max Range: 1.0277. Min Range: -1.0277

Max Act: 0.6719. Min Act: -0.0000

Data Index: 819686 (The Pile)

Max Activating Token Index: 304

Text #16

Max Range: 1.0277. Min Range: -1.0277

Max Act: 0.6436. Min Act: 0.0000

Data Index: 17153 (The Pile)

Max Activating Token Index: 499

Text #17

Max Range: 1.0277. Min Range: -1.0277

Max Act: 0.6436. Min Act: -0.0000

Data Index: 1974537 (The Pile)

Max Activating Token Index: 953

Text #18

Max Range: 1.0277. Min Range: -1.0277

Max Act: 0.6499. Min Act: -0.0000

Data Index: 849149 (The Pile)

Max Activating Token Index: 163

Text #19

Max Range: 1.0277. Min Range: -1.0277

Max Act: 0.6151. Min Act: -0.0000

Data Index: 158855 (The Pile)

Max Activating Token Index: 329