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

Dataset: The Pile

Neuron 783 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8296. Min Range: -0.8296

Max Act: 0.8296. Min Act: -0.0000

Data Index: 13977 (The Pile)

Max Activating Token Index: 412

Text #1

Max Range: 0.8296. Min Range: -0.8296

Max Act: 0.8184. Min Act: -0.0000

Data Index: 1945948 (The Pile)

Max Activating Token Index: 780

Text #2

Max Range: 0.8296. Min Range: -0.8296

Max Act: 0.7899. Min Act: -0.0000

Data Index: 1436070 (The Pile)

Max Activating Token Index: 329

Text #3

Max Range: 0.8296. Min Range: -0.8296

Max Act: 0.7752. Min Act: -0.0000

Data Index: 936693 (The Pile)

Max Activating Token Index: 1014

Text #4

Max Range: 0.8296. Min Range: -0.8296

Max Act: 0.6521. Min Act: -0.0000

Data Index: 44835 (The Pile)

Max Activating Token Index: 644

Text #5

Max Range: 0.8296. Min Range: -0.8296

Max Act: 0.7018. Min Act: -0.0000

Data Index: 1433313 (The Pile)

Max Activating Token Index: 646

Text #6

Max Range: 0.8296. Min Range: -0.8296

Max Act: 0.7230. Min Act: -0.0000

Data Index: 749667 (The Pile)

Max Activating Token Index: 545

Text #7

Max Range: 0.8296. Min Range: -0.8296

Max Act: 0.7122. Min Act: -0.0000

Data Index: 766234 (The Pile)

Max Activating Token Index: 204

Text #8

Max Range: 0.8296. Min Range: -0.8296

Max Act: 0.7669. Min Act: -0.0000

Data Index: 1490790 (The Pile)

Max Activating Token Index: 185

Text #9

Max Range: 0.8296. Min Range: -0.8296

Max Act: 0.7180. Min Act: -0.0000

Data Index: 1105217 (The Pile)

Max Activating Token Index: 381

Text #10

Max Range: 0.8296. Min Range: -0.8296

Max Act: 0.6883. Min Act: -0.0000

Data Index: 129984 (The Pile)

Max Activating Token Index: 295

Text #11

Max Range: 0.8296. Min Range: -0.8296

Max Act: 0.7646. Min Act: -0.0000

Data Index: 1468546 (The Pile)

Max Activating Token Index: 613

Text #12

Max Range: 0.8296. Min Range: -0.8296

Max Act: 0.6895. Min Act: -0.0000

Data Index: 940359 (The Pile)

Max Activating Token Index: 669

Text #13

Max Range: 0.8296. Min Range: -0.8296

Max Act: 0.6594. Min Act: -0.0000

Data Index: 35146 (The Pile)

Max Activating Token Index: 696

Text #14

Max Range: 0.8296. Min Range: -0.8296

Max Act: 0.6820. Min Act: -0.0000

Data Index: 1049583 (The Pile)

Max Activating Token Index: 781

Text #15

Max Range: 0.8296. Min Range: -0.8296

Max Act: 0.6554. Min Act: -0.0000

Data Index: 1178215 (The Pile)

Max Activating Token Index: 778

Text #16

Max Range: 0.8296. Min Range: -0.8296

Max Act: 0.6966. Min Act: -0.0000

Data Index: 1623433 (The Pile)

Max Activating Token Index: 341

Text #17

Max Range: 0.8296. Min Range: -0.8296

Max Act: 0.6431. Min Act: -0.0000

Data Index: 642664 (The Pile)

Max Activating Token Index: 317

Text #18

Max Range: 0.8296. Min Range: -0.8296

Max Act: 0.6548. Min Act: -0.0000

Data Index: 47308 (The Pile)

Max Activating Token Index: 61

Text #19

Max Range: 0.8296. Min Range: -0.8296

Max Act: 0.6467. Min Act: -0.0000

Data Index: 342099 (The Pile)

Max Activating Token Index: 815