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

Dataset: The Pile

Neuron 379 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: 1.4096. Min Range: -1.4096

Max Act: 1.4096. Min Act: -0.0000

Data Index: 785103 (The Pile)

Max Activating Token Index: 1008

Text #1

Max Range: 1.4096. Min Range: -1.4096

Max Act: 1.1413. Min Act: -0.0000

Data Index: 76545 (The Pile)

Max Activating Token Index: 737

Text #2

Max Range: 1.4096. Min Range: -1.4096

Max Act: 1.1668. Min Act: -0.0000

Data Index: 248992 (The Pile)

Max Activating Token Index: 198

Text #3

Max Range: 1.4096. Min Range: -1.4096

Max Act: 1.0897. Min Act: -0.0000

Data Index: 1540408 (The Pile)

Max Activating Token Index: 819

Text #4

Max Range: 1.4096. Min Range: -1.4096

Max Act: 1.0163. Min Act: -0.0000

Data Index: 470512 (The Pile)

Max Activating Token Index: 796

Text #5

Max Range: 1.4096. Min Range: -1.4096

Max Act: 1.0429. Min Act: -0.0000

Data Index: 1620528 (The Pile)

Max Activating Token Index: 110

Text #6

Max Range: 1.4096. Min Range: -1.4096

Max Act: 1.0526. Min Act: -0.0000

Data Index: 70523 (The Pile)

Max Activating Token Index: 420

Text #7

Max Range: 1.4096. Min Range: -1.4096

Max Act: 1.0021. Min Act: -0.0000

Data Index: 620770 (The Pile)

Max Activating Token Index: 925

Text #8

Max Range: 1.4096. Min Range: -1.4096

Max Act: 1.0240. Min Act: -0.0000

Data Index: 467593 (The Pile)

Max Activating Token Index: 728

Text #9

Max Range: 1.4096. Min Range: -1.4096

Max Act: 1.0333. Min Act: -0.0000

Data Index: 336207 (The Pile)

Max Activating Token Index: 1008

Text #10

Max Range: 1.4096. Min Range: -1.4096

Max Act: 0.9815. Min Act: -0.0000

Data Index: 1939775 (The Pile)

Max Activating Token Index: 637

Text #11

Max Range: 1.4096. Min Range: -1.4096

Max Act: 0.9640. Min Act: -0.0000

Data Index: 19522 (The Pile)

Max Activating Token Index: 398

Text #12

Max Range: 1.4096. Min Range: -1.4096

Max Act: 0.9044. Min Act: -0.0000

Data Index: 1393876 (The Pile)

Max Activating Token Index: 50

Text #13

Max Range: 1.4096. Min Range: -1.4096

Max Act: 0.9684. Min Act: -0.0000

Data Index: 395618 (The Pile)

Max Activating Token Index: 526

Text #14

Max Range: 1.4096. Min Range: -1.4096

Max Act: 0.9459. Min Act: -0.0000

Data Index: 193985 (The Pile)

Max Activating Token Index: 346

Text #15

Max Range: 1.4096. Min Range: -1.4096

Max Act: 0.8821. Min Act: -0.0000

Data Index: 1153955 (The Pile)

Max Activating Token Index: 477

Text #16

Max Range: 1.4096. Min Range: -1.4096

Max Act: 0.9059. Min Act: -0.0000

Data Index: 1707284 (The Pile)

Max Activating Token Index: 229

Text #17

Max Range: 1.4096. Min Range: -1.4096

Max Act: 0.8803. Min Act: -0.0000

Data Index: 760510 (The Pile)

Max Activating Token Index: 532

Text #18

Max Range: 1.4096. Min Range: -1.4096

Max Act: 0.8737. Min Act: -0.0000

Data Index: 251942 (The Pile)

Max Activating Token Index: 462

Text #19

Max Range: 1.4096. Min Range: -1.4096

Max Act: 0.9197. Min Act: -0.0000

Data Index: 995240 (The Pile)

Max Activating Token Index: 992