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

Dataset: The Pile

Neuron 1112 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7438. Min Range: -0.7438

Max Act: 0.6696. Min Act: -0.0000

Data Index: 1842362 (The Pile)

Max Activating Token Index: 225

Text #1

Max Range: 0.7438. Min Range: -0.7438

Max Act: 0.6456. Min Act: -0.0000

Data Index: 1295842 (The Pile)

Max Activating Token Index: 294

Text #2

Max Range: 0.7438. Min Range: -0.7438

Max Act: 0.7438. Min Act: -0.0000

Data Index: 1132166 (The Pile)

Max Activating Token Index: 585

Text #3

Max Range: 0.7438. Min Range: -0.7438

Max Act: 0.5771. Min Act: -0.0000

Data Index: 842316 (The Pile)

Max Activating Token Index: 499

Text #4

Max Range: 0.7438. Min Range: -0.7438

Max Act: 0.6024. Min Act: -0.0000

Data Index: 400510 (The Pile)

Max Activating Token Index: 488

Text #5

Max Range: 0.7438. Min Range: -0.7438

Max Act: 0.5893. Min Act: -0.0000

Data Index: 429590 (The Pile)

Max Activating Token Index: 249

Text #6

Max Range: 0.7438. Min Range: -0.7438

Max Act: 0.6273. Min Act: -0.0000

Data Index: 40936 (The Pile)

Max Activating Token Index: 263

Text #7

Max Range: 0.7438. Min Range: -0.7438

Max Act: 0.6682. Min Act: -0.0000

Data Index: 568468 (The Pile)

Max Activating Token Index: 306

Text #8

Max Range: 0.7438. Min Range: -0.7438

Max Act: 0.5329. Min Act: -0.0000

Data Index: 1652767 (The Pile)

Max Activating Token Index: 755

Text #9

Max Range: 0.7438. Min Range: -0.7438

Max Act: 0.6373. Min Act: -0.0000

Data Index: 53387 (The Pile)

Max Activating Token Index: 622

Text #10

Max Range: 0.7438. Min Range: -0.7438

Max Act: 0.5723. Min Act: -0.0000

Data Index: 695008 (The Pile)

Max Activating Token Index: 261

Text #11

Max Range: 0.7438. Min Range: -0.7438

Max Act: 0.6211. Min Act: -0.0000

Data Index: 1712676 (The Pile)

Max Activating Token Index: 638

Text #12

Max Range: 0.7438. Min Range: -0.7438

Max Act: 0.6028. Min Act: -0.0000

Data Index: 347874 (The Pile)

Max Activating Token Index: 313

Text #13

Max Range: 0.7438. Min Range: -0.7438

Max Act: 0.6599. Min Act: -0.0000

Data Index: 541705 (The Pile)

Max Activating Token Index: 671

Text #14

Max Range: 0.7438. Min Range: -0.7438

Max Act: 0.5557. Min Act: -0.0000

Data Index: 776165 (The Pile)

Max Activating Token Index: 373

Text #15

Max Range: 0.7438. Min Range: -0.7438

Max Act: 0.5839. Min Act: -0.0000

Data Index: 577711 (The Pile)

Max Activating Token Index: 151

Text #16

Max Range: 0.7438. Min Range: -0.7438

Max Act: 0.6040. Min Act: -0.0000

Data Index: 137226 (The Pile)

Max Activating Token Index: 94

Text #17

Max Range: 0.7438. Min Range: -0.7438

Max Act: 0.5893. Min Act: -0.0000

Data Index: 426968 (The Pile)

Max Activating Token Index: 582

Text #18

Max Range: 0.7438. Min Range: -0.7438

Max Act: 0.6340. Min Act: -0.0000

Data Index: 440526 (The Pile)

Max Activating Token Index: 130

Text #19

Max Range: 0.7438. Min Range: -0.7438

Max Act: 0.5842. Min Act: -0.0000

Data Index: 1472780 (The Pile)

Max Activating Token Index: 247