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

Dataset: The Pile

Neuron 160 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: 1.8882. Min Range: -1.8882

Max Act: 1.8882. Min Act: -0.0000

Data Index: 1410443 (The Pile)

Max Activating Token Index: 93

Text #1

Max Range: 1.8882. Min Range: -1.8882

Max Act: 1.6495. Min Act: -0.0000

Data Index: 646943 (The Pile)

Max Activating Token Index: 600

Text #2

Max Range: 1.8882. Min Range: -1.8882

Max Act: 1.6549. Min Act: -0.0000

Data Index: 1831255 (The Pile)

Max Activating Token Index: 53

Text #3

Max Range: 1.8882. Min Range: -1.8882

Max Act: 1.5268. Min Act: -0.0000

Data Index: 1855824 (The Pile)

Max Activating Token Index: 145

Text #4

Max Range: 1.8882. Min Range: -1.8882

Max Act: 1.5919. Min Act: -0.0000

Data Index: 293478 (The Pile)

Max Activating Token Index: 138

Text #5

Max Range: 1.8882. Min Range: -1.8882

Max Act: 1.4988. Min Act: -0.0000

Data Index: 413745 (The Pile)

Max Activating Token Index: 339

Text #6

Max Range: 1.8882. Min Range: -1.8882

Max Act: 1.5743. Min Act: -0.0000

Data Index: 1949376 (The Pile)

Max Activating Token Index: 211

Text #7

Max Range: 1.8882. Min Range: -1.8882

Max Act: 1.5359. Min Act: -0.0000

Data Index: 456544 (The Pile)

Max Activating Token Index: 74

Text #8

Max Range: 1.8882. Min Range: -1.8882

Max Act: 1.4548. Min Act: -0.0000

Data Index: 1722492 (The Pile)

Max Activating Token Index: 517

Text #9

Max Range: 1.8882. Min Range: -1.8882

Max Act: 1.6139. Min Act: -0.0000

Data Index: 582532 (The Pile)

Max Activating Token Index: 16

Text #10

Max Range: 1.8882. Min Range: -1.8882

Max Act: 1.4118. Min Act: -0.0000

Data Index: 552830 (The Pile)

Max Activating Token Index: 270

Text #11

Max Range: 1.8882. Min Range: -1.8882

Max Act: 1.4849. Min Act: -0.0000

Data Index: 443513 (The Pile)

Max Activating Token Index: 473

Text #12

Max Range: 1.8882. Min Range: -1.8882

Max Act: 1.4293. Min Act: -0.0000

Data Index: 424928 (The Pile)

Max Activating Token Index: 55

Text #13

Max Range: 1.8882. Min Range: -1.8882

Max Act: 1.4037. Min Act: -0.0000

Data Index: 1128160 (The Pile)

Max Activating Token Index: 595

Text #14

Max Range: 1.8882. Min Range: -1.8882

Max Act: 1.4224. Min Act: -0.0000

Data Index: 949018 (The Pile)

Max Activating Token Index: 80

Text #15

Max Range: 1.8882. Min Range: -1.8882

Max Act: 1.3292. Min Act: -0.0000

Data Index: 1121201 (The Pile)

Max Activating Token Index: 561

Text #16

Max Range: 1.8882. Min Range: -1.8882

Max Act: 1.4950. Min Act: -0.0000

Data Index: 1976251 (The Pile)

Max Activating Token Index: 458

Text #17

Max Range: 1.8882. Min Range: -1.8882

Max Act: 1.3485. Min Act: -0.0000

Data Index: 1442150 (The Pile)

Max Activating Token Index: 81

Text #18

Max Range: 1.8882. Min Range: -1.8882

Max Act: 1.2037. Min Act: -0.0000

Data Index: 390343 (The Pile)

Max Activating Token Index: 163

Text #19

Max Range: 1.8882. Min Range: -1.8882

Max Act: 1.3369. Min Act: -0.0000

Data Index: 1018793 (The Pile)

Max Activating Token Index: 498