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

Dataset: The Pile

Neuron 3438 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8406. Min Range: -0.8406

Max Act: 0.8406. Min Act: -0.0000

Data Index: 1078769 (The Pile)

Max Activating Token Index: 196

Text #1

Max Range: 0.8406. Min Range: -0.8406

Max Act: 0.7892. Min Act: -0.0000

Data Index: 247997 (The Pile)

Max Activating Token Index: 307

Text #2

Max Range: 0.8406. Min Range: -0.8406

Max Act: 0.7735. Min Act: -0.0000

Data Index: 719952 (The Pile)

Max Activating Token Index: 340

Text #3

Max Range: 0.8406. Min Range: -0.8406

Max Act: 0.8080. Min Act: -0.0000

Data Index: 1430652 (The Pile)

Max Activating Token Index: 834

Text #4

Max Range: 0.8406. Min Range: -0.8406

Max Act: 0.7995. Min Act: 0.0000

Data Index: 1771143 (The Pile)

Max Activating Token Index: 1019

Text #5

Max Range: 0.8406. Min Range: -0.8406

Max Act: 0.7403. Min Act: -0.0000

Data Index: 1056194 (The Pile)

Max Activating Token Index: 264

Text #6

Max Range: 0.8406. Min Range: -0.8406

Max Act: 0.7370. Min Act: 0.0000

Data Index: 1648927 (The Pile)

Max Activating Token Index: 662

Text #7

Max Range: 0.8406. Min Range: -0.8406

Max Act: 0.7262. Min Act: -0.0000

Data Index: 685338 (The Pile)

Max Activating Token Index: 239

Text #8

Max Range: 0.8406. Min Range: -0.8406

Max Act: 0.7298. Min Act: 0.0000

Data Index: 306249 (The Pile)

Max Activating Token Index: 44

Text #9

Max Range: 0.8406. Min Range: -0.8406

Max Act: 0.7108. Min Act: -0.0000

Data Index: 1860878 (The Pile)

Max Activating Token Index: 403

Text #10

Max Range: 0.8406. Min Range: -0.8406

Max Act: 0.7141. Min Act: 0.0000

Data Index: 1976507 (The Pile)

Max Activating Token Index: 666

Text #11

Max Range: 0.8406. Min Range: -0.8406

Max Act: 0.6767. Min Act: 0.0000

Data Index: 1763644 (The Pile)

Max Activating Token Index: 218

Text #12

Max Range: 0.8406. Min Range: -0.8406

Max Act: 0.6709. Min Act: -0.0000

Data Index: 1174095 (The Pile)

Max Activating Token Index: 210

Text #13

Max Range: 0.8406. Min Range: -0.8406

Max Act: 0.6657. Min Act: -0.0000

Data Index: 199244 (The Pile)

Max Activating Token Index: 273

Text #14

Max Range: 0.8406. Min Range: -0.8406

Max Act: 0.6861. Min Act: 0.0000

Data Index: 1076632 (The Pile)

Max Activating Token Index: 336

Text #15

Max Range: 0.8406. Min Range: -0.8406

Max Act: 0.6879. Min Act: -0.0000

Data Index: 545786 (The Pile)

Max Activating Token Index: 304

Text #16

Max Range: 0.8406. Min Range: -0.8406

Max Act: 0.7061. Min Act: -0.0000

Data Index: 850982 (The Pile)

Max Activating Token Index: 157

Text #17

Max Range: 0.8406. Min Range: -0.8406

Max Act: 0.6304. Min Act: 0.0000

Data Index: 832565 (The Pile)

Max Activating Token Index: 569

Text #18

Max Range: 0.8406. Min Range: -0.8406

Max Act: 0.6574. Min Act: -0.0000

Data Index: 787385 (The Pile)

Max Activating Token Index: 26

Text #19

Max Range: 0.8406. Min Range: -0.8406

Max Act: 0.6351. Min Act: -0.0000

Data Index: 1498662 (The Pile)

Max Activating Token Index: 322