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

Dataset: The Pile

Neuron 2094 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9426. Min Range: -3.9426

Max Act: 3.9426. Min Act: -0.0000

Data Index: 602415 (The Pile)

Max Activating Token Index: 449

Text #1

Max Range: 3.9426. Min Range: -3.9426

Max Act: 3.6552. Min Act: -0.0000

Data Index: 1521656 (The Pile)

Max Activating Token Index: 507

Text #2

Max Range: 3.9426. Min Range: -3.9426

Max Act: 3.6091. Min Act: -0.0000

Data Index: 1388441 (The Pile)

Max Activating Token Index: 749

Text #3

Max Range: 3.9426. Min Range: -3.9426

Max Act: 3.5512. Min Act: -0.0000

Data Index: 1546915 (The Pile)

Max Activating Token Index: 188

Text #4

Max Range: 3.9426. Min Range: -3.9426

Max Act: 3.3029. Min Act: -0.0000

Data Index: 1650427 (The Pile)

Max Activating Token Index: 684

Text #5

Max Range: 3.9426. Min Range: -3.9426

Max Act: 3.3909. Min Act: -0.0000

Data Index: 1588823 (The Pile)

Max Activating Token Index: 742

Text #6

Max Range: 3.9426. Min Range: -3.9426

Max Act: 3.5270. Min Act: -0.0000

Data Index: 188655 (The Pile)

Max Activating Token Index: 216

Text #7

Max Range: 3.9426. Min Range: -3.9426

Max Act: 3.6514. Min Act: -0.0000

Data Index: 742959 (The Pile)

Max Activating Token Index: 653

Text #8

Max Range: 3.9426. Min Range: -3.9426

Max Act: 3.0200. Min Act: -0.0000

Data Index: 1125761 (The Pile)

Max Activating Token Index: 498

Text #9

Max Range: 3.9426. Min Range: -3.9426

Max Act: 2.8531. Min Act: -0.0000

Data Index: 1147371 (The Pile)

Max Activating Token Index: 1008

Text #10

Max Range: 3.9426. Min Range: -3.9426

Max Act: 2.9636. Min Act: -0.0000

Data Index: 391539 (The Pile)

Max Activating Token Index: 184

Text #11

Max Range: 3.9426. Min Range: -3.9426

Max Act: 3.0648. Min Act: -0.0000

Data Index: 1177638 (The Pile)

Max Activating Token Index: 786

Text #12

Max Range: 3.9426. Min Range: -3.9426

Max Act: 3.2308. Min Act: -0.0000

Data Index: 1937534 (The Pile)

Max Activating Token Index: 371

Text #13

Max Range: 3.9426. Min Range: -3.9426

Max Act: 2.8887. Min Act: -0.0000

Data Index: 1622482 (The Pile)

Max Activating Token Index: 409

Text #14

Max Range: 3.9426. Min Range: -3.9426

Max Act: 3.0242. Min Act: -0.0000

Data Index: 479436 (The Pile)

Max Activating Token Index: 929

Text #15

Max Range: 3.9426. Min Range: -3.9426

Max Act: 2.8812. Min Act: -0.0000

Data Index: 17402 (The Pile)

Max Activating Token Index: 375

Text #16

Max Range: 3.9426. Min Range: -3.9426

Max Act: 3.0296. Min Act: -0.0000

Data Index: 391222 (The Pile)

Max Activating Token Index: 868

Text #17

Max Range: 3.9426. Min Range: -3.9426

Max Act: 2.8547. Min Act: -0.0000

Data Index: 121608 (The Pile)

Max Activating Token Index: 243

Text #18

Max Range: 3.9426. Min Range: -3.9426

Max Act: 3.1069. Min Act: -0.0000

Data Index: 487948 (The Pile)

Max Activating Token Index: 571

Text #19

Max Range: 3.9426. Min Range: -3.9426

Max Act: 2.9186. Min Act: -0.0000

Data Index: 182096 (The Pile)

Max Activating Token Index: 949