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

Dataset: The Pile

Neuron 436 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.7424. Min Act: -0.0000

Data Index: 131619 (The Pile)

Max Activating Token Index: 534

Text #1

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.6255. Min Act: -0.0000

Data Index: 627408 (The Pile)

Max Activating Token Index: 107

Text #2

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.4826. Min Act: -0.0000

Data Index: 1292853 (The Pile)

Max Activating Token Index: 84

Text #3

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.5689. Min Act: -0.0000

Data Index: 268182 (The Pile)

Max Activating Token Index: 182

Text #4

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.5219. Min Act: -0.0000

Data Index: 740914 (The Pile)

Max Activating Token Index: 554

Text #5

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.4597. Min Act: -0.0000

Data Index: 887711 (The Pile)

Max Activating Token Index: 129

Text #6

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.4380. Min Act: -0.0000

Data Index: 1440060 (The Pile)

Max Activating Token Index: 149

Text #7

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.3885. Min Act: -0.0000

Data Index: 1114381 (The Pile)

Max Activating Token Index: 901

Text #8

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.4145. Min Act: -0.0000

Data Index: 1686346 (The Pile)

Max Activating Token Index: 188

Text #9

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.4496. Min Act: -0.0000

Data Index: 1676248 (The Pile)

Max Activating Token Index: 12

Text #10

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.4061. Min Act: -0.0000

Data Index: 757493 (The Pile)

Max Activating Token Index: 290

Text #11

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.3574. Min Act: -0.0000

Data Index: 1548439 (The Pile)

Max Activating Token Index: 853

Text #12

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.3262. Min Act: -0.0000

Data Index: 1230337 (The Pile)

Max Activating Token Index: 566

Text #13

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.3235. Min Act: -0.0000

Data Index: 806735 (The Pile)

Max Activating Token Index: 178

Text #14

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.3494. Min Act: -0.0000

Data Index: 1386289 (The Pile)

Max Activating Token Index: 419

Text #15

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.2745. Min Act: -0.0000

Data Index: 1902105 (The Pile)

Max Activating Token Index: 704

Text #16

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.3463. Min Act: -0.0000

Data Index: 1260608 (The Pile)

Max Activating Token Index: 162

Text #17

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.3089. Min Act: -0.0000

Data Index: 599539 (The Pile)

Max Activating Token Index: 371

Text #18

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.0855. Min Act: -0.0000

Data Index: 1327186 (The Pile)

Max Activating Token Index: 762

Text #19

Max Range: 1.7424. Min Range: -1.7424

Max Act: 1.3782. Min Act: -0.0000

Data Index: 1578857 (The Pile)

Max Activating Token Index: 578