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

Dataset: The Pile

Neuron 5057 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2255. Min Range: -1.2255

Max Act: 1.2255. Min Act: -0.0000

Data Index: 365955 (The Pile)

Max Activating Token Index: 851

Text #1

Max Range: 1.2255. Min Range: -1.2255

Max Act: 1.1333. Min Act: -0.0000

Data Index: 905520 (The Pile)

Max Activating Token Index: 369

Text #2

Max Range: 1.2255. Min Range: -1.2255

Max Act: 1.1546. Min Act: -0.0000

Data Index: 857198 (The Pile)

Max Activating Token Index: 238

Text #3

Max Range: 1.2255. Min Range: -1.2255

Max Act: 1.1587. Min Act: -0.0000

Data Index: 1289917 (The Pile)

Max Activating Token Index: 596

Text #4

Max Range: 1.2255. Min Range: -1.2255

Max Act: 1.0999. Min Act: -0.0000

Data Index: 720587 (The Pile)

Max Activating Token Index: 585

Text #5

Max Range: 1.2255. Min Range: -1.2255

Max Act: 1.0255. Min Act: -0.0000

Data Index: 410725 (The Pile)

Max Activating Token Index: 940

Text #6

Max Range: 1.2255. Min Range: -1.2255

Max Act: 1.0241. Min Act: -0.0000

Data Index: 1052248 (The Pile)

Max Activating Token Index: 42

Text #7

Max Range: 1.2255. Min Range: -1.2255

Max Act: 1.0322. Min Act: -0.0000

Data Index: 629648 (The Pile)

Max Activating Token Index: 405

Text #8

Max Range: 1.2255. Min Range: -1.2255

Max Act: 0.9863. Min Act: -0.0000

Data Index: 737291 (The Pile)

Max Activating Token Index: 995

Text #9

Max Range: 1.2255. Min Range: -1.2255

Max Act: 0.9573. Min Act: -0.0000

Data Index: 1123900 (The Pile)

Max Activating Token Index: 977

Text #10

Max Range: 1.2255. Min Range: -1.2255

Max Act: 1.0512. Min Act: -0.0000

Data Index: 311092 (The Pile)

Max Activating Token Index: 900

Text #11

Max Range: 1.2255. Min Range: -1.2255

Max Act: 0.9552. Min Act: -0.0000

Data Index: 1576558 (The Pile)

Max Activating Token Index: 662

Text #12

Max Range: 1.2255. Min Range: -1.2255

Max Act: 0.9694. Min Act: -0.0001

Data Index: 1639780 (The Pile)

Max Activating Token Index: 941

Text #13

Max Range: 1.2255. Min Range: -1.2255

Max Act: 0.9721. Min Act: -0.0000

Data Index: 266911 (The Pile)

Max Activating Token Index: 306

Text #14

Max Range: 1.2255. Min Range: -1.2255

Max Act: 0.9968. Min Act: -0.0000

Data Index: 640288 (The Pile)

Max Activating Token Index: 596

Text #15

Max Range: 1.2255. Min Range: -1.2255

Max Act: 0.9276. Min Act: -0.0000

Data Index: 1079810 (The Pile)

Max Activating Token Index: 565

Text #16

Max Range: 1.2255. Min Range: -1.2255

Max Act: 0.9545. Min Act: -0.0000

Data Index: 55413 (The Pile)

Max Activating Token Index: 65

Text #17

Max Range: 1.2255. Min Range: -1.2255

Max Act: 0.9228. Min Act: -0.0000

Data Index: 1677038 (The Pile)

Max Activating Token Index: 632

Text #18

Max Range: 1.2255. Min Range: -1.2255

Max Act: 0.9318. Min Act: -0.0000

Data Index: 1147773 (The Pile)

Max Activating Token Index: 316

Text #19

Max Range: 1.2255. Min Range: -1.2255

Max Act: 0.8977. Min Act: -0.0000

Data Index: 247101 (The Pile)

Max Activating Token Index: 519