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

Dataset: The Pile

Neuron 1571 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: 0.4534. Min Range: -0.4534

Max Act: 0.4534. Min Act: -0.0000

Data Index: 1074420 (The Pile)

Max Activating Token Index: 472

Text #1

Max Range: 0.4534. Min Range: -0.4534

Max Act: 0.3488. Min Act: -0.0000

Data Index: 530345 (The Pile)

Max Activating Token Index: 235

Text #2

Max Range: 0.4534. Min Range: -0.4534

Max Act: 0.3511. Min Act: -0.0000

Data Index: 115108 (The Pile)

Max Activating Token Index: 404

Text #3

Max Range: 0.4534. Min Range: -0.4534

Max Act: 0.3499. Min Act: -0.0000

Data Index: 115933 (The Pile)

Max Activating Token Index: 733

Text #4

Max Range: 0.4534. Min Range: -0.4534

Max Act: 0.3174. Min Act: -0.0000

Data Index: 695540 (The Pile)

Max Activating Token Index: 1020

Text #5

Max Range: 0.4534. Min Range: -0.4534

Max Act: 0.3272. Min Act: -0.0000

Data Index: 1454744 (The Pile)

Max Activating Token Index: 561

Text #6

Max Range: 0.4534. Min Range: -0.4534

Max Act: 0.3330. Min Act: -0.0000

Data Index: 1220777 (The Pile)

Max Activating Token Index: 354

Text #7

Max Range: 0.4534. Min Range: -0.4534

Max Act: 0.3002. Min Act: -0.0000

Data Index: 1203716 (The Pile)

Max Activating Token Index: 552

Text #8

Max Range: 0.4534. Min Range: -0.4534

Max Act: 0.3319. Min Act: -0.0000

Data Index: 1442923 (The Pile)

Max Activating Token Index: 973

Text #9

Max Range: 0.4534. Min Range: -0.4534

Max Act: 0.3153. Min Act: -0.0000

Data Index: 1234354 (The Pile)

Max Activating Token Index: 575

Text #10

Max Range: 0.4534. Min Range: -0.4534

Max Act: 0.3240. Min Act: -0.0000

Data Index: 360969 (The Pile)

Max Activating Token Index: 832

Text #11

Max Range: 0.4534. Min Range: -0.4534

Max Act: 0.2956. Min Act: -0.0000

Data Index: 111552 (The Pile)

Max Activating Token Index: 137

Text #12

Max Range: 0.4534. Min Range: -0.4534

Max Act: 0.3044. Min Act: -0.0000

Data Index: 1762953 (The Pile)

Max Activating Token Index: 869

Text #13

Max Range: 0.4534. Min Range: -0.4534

Max Act: 0.3257. Min Act: -0.0000

Data Index: 1306865 (The Pile)

Max Activating Token Index: 616

Text #14

Max Range: 0.4534. Min Range: -0.4534

Max Act: 0.3147. Min Act: -0.0000

Data Index: 503545 (The Pile)

Max Activating Token Index: 369

Text #15

Max Range: 0.4534. Min Range: -0.4534

Max Act: 0.2799. Min Act: -0.0000

Data Index: 1418773 (The Pile)

Max Activating Token Index: 896

Text #16

Max Range: 0.4534. Min Range: -0.4534

Max Act: 0.2875. Min Act: -0.0000

Data Index: 952316 (The Pile)

Max Activating Token Index: 174

Text #17

Max Range: 0.4534. Min Range: -0.4534

Max Act: 0.2841. Min Act: -0.0000

Data Index: 1959266 (The Pile)

Max Activating Token Index: 801

Text #18

Max Range: 0.4534. Min Range: -0.4534

Max Act: 0.2841. Min Act: -0.0000

Data Index: 1539461 (The Pile)

Max Activating Token Index: 843

Text #19

Max Range: 0.4534. Min Range: -0.4534

Max Act: 0.3176. Min Act: -0.0000

Data Index: 617032 (The Pile)

Max Activating Token Index: 774