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

Dataset: The Pile

Neuron 2316 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.4892. Min Act: -0.0000

Data Index: 393711 (The Pile)

Max Activating Token Index: 756

Text #1

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.4679. Min Act: -0.0000

Data Index: 136587 (The Pile)

Max Activating Token Index: 186

Text #2

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.4982. Min Act: -0.0000

Data Index: 95524 (The Pile)

Max Activating Token Index: 379

Text #3

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.4826. Min Act: -0.0000

Data Index: 1999217 (The Pile)

Max Activating Token Index: 870

Text #4

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.4707. Min Act: -0.0000

Data Index: 1239991 (The Pile)

Max Activating Token Index: 714

Text #5

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.4565. Min Act: -0.0000

Data Index: 468162 (The Pile)

Max Activating Token Index: 193

Text #6

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.4532. Min Act: -0.0000

Data Index: 1648133 (The Pile)

Max Activating Token Index: 256

Text #7

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.4543. Min Act: -0.0000

Data Index: 1137973 (The Pile)

Max Activating Token Index: 542

Text #8

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.4503. Min Act: -0.0000

Data Index: 798547 (The Pile)

Max Activating Token Index: 586

Text #9

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.4624. Min Act: -0.0000

Data Index: 196641 (The Pile)

Max Activating Token Index: 44

Text #10

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.4742. Min Act: -0.0000

Data Index: 1937489 (The Pile)

Max Activating Token Index: 289

Text #11

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.4573. Min Act: -0.0000

Data Index: 1432553 (The Pile)

Max Activating Token Index: 825

Text #12

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.4646. Min Act: -0.0000

Data Index: 965544 (The Pile)

Max Activating Token Index: 111

Text #13

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.4425. Min Act: -0.0000

Data Index: 1712578 (The Pile)

Max Activating Token Index: 868

Text #14

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.4603. Min Act: -0.0000

Data Index: 358510 (The Pile)

Max Activating Token Index: 120

Text #15

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.4466. Min Act: -0.0000

Data Index: 1811271 (The Pile)

Max Activating Token Index: 271

Text #16

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.4413. Min Act: -0.0000

Data Index: 473887 (The Pile)

Max Activating Token Index: 360

Text #17

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.4369. Min Act: -0.0000

Data Index: 1002971 (The Pile)

Max Activating Token Index: 243

Text #18

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3981. Min Act: -0.0000

Data Index: 320599 (The Pile)

Max Activating Token Index: 722

Text #19

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.4371. Min Act: -0.0000

Data Index: 420822 (The Pile)

Max Activating Token Index: 259