Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 772 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.3754. Min Range: -0.3754

Max Act: 0.3664. Min Act: -0.0000

Data Index: 1201236 (The Pile)

Max Activating Token Index: 806

Text #1

Max Range: 0.3754. Min Range: -0.3754

Max Act: 0.3754. Min Act: -0.0000

Data Index: 389377 (The Pile)

Max Activating Token Index: 668

Text #2

Max Range: 0.3754. Min Range: -0.3754

Max Act: 0.3617. Min Act: -0.0001

Data Index: 899548 (The Pile)

Max Activating Token Index: 935

Text #3

Max Range: 0.3754. Min Range: -0.3754

Max Act: 0.3665. Min Act: -0.0000

Data Index: 613890 (The Pile)

Max Activating Token Index: 726

Text #4

Max Range: 0.3754. Min Range: -0.3754

Max Act: 0.3475. Min Act: -0.0000

Data Index: 715213 (The Pile)

Max Activating Token Index: 402

Text #5

Max Range: 0.3754. Min Range: -0.3754

Max Act: 0.3428. Min Act: -0.0000

Data Index: 1006065 (The Pile)

Max Activating Token Index: 245

Text #6

Max Range: 0.3754. Min Range: -0.3754

Max Act: 0.3421. Min Act: 0.0000

Data Index: 1460556 (The Pile)

Max Activating Token Index: 56

Text #7

Max Range: 0.3754. Min Range: -0.3754

Max Act: 0.3333. Min Act: 0.0001

Data Index: 279563 (The Pile)

Max Activating Token Index: 56

Text #8

Max Range: 0.3754. Min Range: -0.3754

Max Act: 0.3367. Min Act: 0.0002

Data Index: 1123367 (The Pile)

Max Activating Token Index: 484

Text #9

Max Range: 0.3754. Min Range: -0.3754

Max Act: 0.3579. Min Act: -0.0000

Data Index: 1446953 (The Pile)

Max Activating Token Index: 116

Text #10

Max Range: 0.3754. Min Range: -0.3754

Max Act: 0.3331. Min Act: -0.0000

Data Index: 1406050 (The Pile)

Max Activating Token Index: 76

Text #11

Max Range: 0.3754. Min Range: -0.3754

Max Act: 0.3177. Min Act: -0.0000

Data Index: 646911 (The Pile)

Max Activating Token Index: 968

Text #12

Max Range: 0.3754. Min Range: -0.3754

Max Act: 0.3244. Min Act: 0.0000

Data Index: 501756 (The Pile)

Max Activating Token Index: 110

Text #13

Max Range: 0.3754. Min Range: -0.3754

Max Act: 0.3157. Min Act: -0.0000

Data Index: 1215817 (The Pile)

Max Activating Token Index: 87

Text #14

Max Range: 0.3754. Min Range: -0.3754

Max Act: 0.3122. Min Act: -0.0001

Data Index: 1903438 (The Pile)

Max Activating Token Index: 872

Text #15

Max Range: 0.3754. Min Range: -0.3754

Max Act: 0.3207. Min Act: -0.0001

Data Index: 137583 (The Pile)

Max Activating Token Index: 357

Text #16

Max Range: 0.3754. Min Range: -0.3754

Max Act: 0.3080. Min Act: -0.0000

Data Index: 998217 (The Pile)

Max Activating Token Index: 971

Text #17

Max Range: 0.3754. Min Range: -0.3754

Max Act: 0.2972. Min Act: -0.0000

Data Index: 589452 (The Pile)

Max Activating Token Index: 904

Text #18

Max Range: 0.3754. Min Range: -0.3754

Max Act: 0.3048. Min Act: -0.0001

Data Index: 718557 (The Pile)

Max Activating Token Index: 125

Text #19

Max Range: 0.3754. Min Range: -0.3754

Max Act: 0.2535. Min Act: -0.0000

Data Index: 271604 (The Pile)

Max Activating Token Index: 1022