Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1991 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4848. Min Act: -0.0000

Data Index: 1342373 (The Pile)

Max Activating Token Index: 151

Text #1

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4784. Min Act: -0.0000

Data Index: 1631799 (The Pile)

Max Activating Token Index: 192

Text #2

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.3928. Min Act: -0.0000

Data Index: 1799428 (The Pile)

Max Activating Token Index: 561

Text #3

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.5240. Min Act: -0.0000

Data Index: 1545532 (The Pile)

Max Activating Token Index: 400

Text #4

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4818. Min Act: -0.0000

Data Index: 780104 (The Pile)

Max Activating Token Index: 145

Text #5

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4814. Min Act: -0.0000

Data Index: 1374657 (The Pile)

Max Activating Token Index: 631

Text #6

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4283. Min Act: -0.0000

Data Index: 1076517 (The Pile)

Max Activating Token Index: 44

Text #7

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4421. Min Act: -0.0000

Data Index: 420846 (The Pile)

Max Activating Token Index: 160

Text #8

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4194. Min Act: -0.0000

Data Index: 329516 (The Pile)

Max Activating Token Index: 231

Text #9

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4595. Min Act: -0.0000

Data Index: 1279863 (The Pile)

Max Activating Token Index: 306

Text #10

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.3967. Min Act: -0.0000

Data Index: 251259 (The Pile)

Max Activating Token Index: 391

Text #11

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4075. Min Act: -0.0000

Data Index: 1549516 (The Pile)

Max Activating Token Index: 534

Text #12

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4160. Min Act: -0.0000

Data Index: 1177430 (The Pile)

Max Activating Token Index: 810

Text #13

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4102. Min Act: -0.0000

Data Index: 599173 (The Pile)

Max Activating Token Index: 939

Text #14

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.3575. Min Act: -0.0000

Data Index: 503971 (The Pile)

Max Activating Token Index: 628

Text #15

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.3686. Min Act: -0.0000

Data Index: 1349731 (The Pile)

Max Activating Token Index: 604

Text #16

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.3603. Min Act: -0.0000

Data Index: 1383724 (The Pile)

Max Activating Token Index: 438

Text #17

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.3527. Min Act: -0.0000

Data Index: 1292691 (The Pile)

Max Activating Token Index: 360

Text #18

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.3402. Min Act: -0.0000

Data Index: 295050 (The Pile)

Max Activating Token Index: 157

Text #19

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.3614. Min Act: -0.0000

Data Index: 1524090 (The Pile)

Max Activating Token Index: 294