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

Dataset: The Pile

Neuron 1391 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: 1.8716. Min Range: -1.8716

Max Act: 1.8716. Min Act: -0.0000

Data Index: 1803237 (The Pile)

Max Activating Token Index: 210

Text #1

Max Range: 1.8716. Min Range: -1.8716

Max Act: 1.7109. Min Act: -0.0000

Data Index: 171850 (The Pile)

Max Activating Token Index: 249

Text #2

Max Range: 1.8716. Min Range: -1.8716

Max Act: 1.6755. Min Act: -0.0000

Data Index: 682394 (The Pile)

Max Activating Token Index: 311

Text #3

Max Range: 1.8716. Min Range: -1.8716

Max Act: 1.7787. Min Act: -0.0000

Data Index: 1697249 (The Pile)

Max Activating Token Index: 928

Text #4

Max Range: 1.8716. Min Range: -1.8716

Max Act: 1.7669. Min Act: -0.0000

Data Index: 347480 (The Pile)

Max Activating Token Index: 90

Text #5

Max Range: 1.8716. Min Range: -1.8716

Max Act: 1.6316. Min Act: -0.0000

Data Index: 1685637 (The Pile)

Max Activating Token Index: 814

Text #6

Max Range: 1.8716. Min Range: -1.8716

Max Act: 1.7663. Min Act: -0.0000

Data Index: 1495426 (The Pile)

Max Activating Token Index: 1003

Text #7

Max Range: 1.8716. Min Range: -1.8716

Max Act: 1.5548. Min Act: -0.0000

Data Index: 578417 (The Pile)

Max Activating Token Index: 770

Text #8

Max Range: 1.8716. Min Range: -1.8716

Max Act: 1.5645. Min Act: -0.0000

Data Index: 447360 (The Pile)

Max Activating Token Index: 948

Text #9

Max Range: 1.8716. Min Range: -1.8716

Max Act: 1.6440. Min Act: -0.0000

Data Index: 1973157 (The Pile)

Max Activating Token Index: 410

Text #10

Max Range: 1.8716. Min Range: -1.8716

Max Act: 1.4507. Min Act: -0.0000

Data Index: 1222164 (The Pile)

Max Activating Token Index: 65

Text #11

Max Range: 1.8716. Min Range: -1.8716

Max Act: 1.7072. Min Act: -0.0000

Data Index: 677364 (The Pile)

Max Activating Token Index: 913

Text #12

Max Range: 1.8716. Min Range: -1.8716

Max Act: 1.4783. Min Act: -0.0000

Data Index: 110688 (The Pile)

Max Activating Token Index: 446

Text #13

Max Range: 1.8716. Min Range: -1.8716

Max Act: 1.4706. Min Act: -0.0000

Data Index: 389579 (The Pile)

Max Activating Token Index: 797

Text #14

Max Range: 1.8716. Min Range: -1.8716

Max Act: 1.4522. Min Act: -0.0000

Data Index: 1666741 (The Pile)

Max Activating Token Index: 543

Text #15

Max Range: 1.8716. Min Range: -1.8716

Max Act: 1.5228. Min Act: -0.0000

Data Index: 367327 (The Pile)

Max Activating Token Index: 709

Text #16

Max Range: 1.8716. Min Range: -1.8716

Max Act: 1.4425. Min Act: -0.0000

Data Index: 587558 (The Pile)

Max Activating Token Index: 185

Text #17

Max Range: 1.8716. Min Range: -1.8716

Max Act: 1.3636. Min Act: -0.0000

Data Index: 597371 (The Pile)

Max Activating Token Index: 301

Text #18

Max Range: 1.8716. Min Range: -1.8716

Max Act: 1.3504. Min Act: -0.0000

Data Index: 325448 (The Pile)

Max Activating Token Index: 484

Text #19

Max Range: 1.8716. Min Range: -1.8716

Max Act: 1.4151. Min Act: -0.0000

Data Index: 1058158 (The Pile)

Max Activating Token Index: 97