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

Dataset: The Pile

Neuron 2389 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: 0.8181. Min Range: -0.8181

Max Act: 0.8181. Min Act: -0.0000

Data Index: 1063423 (The Pile)

Max Activating Token Index: 563

Text #1

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.7526. Min Act: -0.0000

Data Index: 1416546 (The Pile)

Max Activating Token Index: 1007

Text #2

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.7411. Min Act: -0.0000

Data Index: 1627545 (The Pile)

Max Activating Token Index: 864

Text #3

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.7396. Min Act: -0.0000

Data Index: 764608 (The Pile)

Max Activating Token Index: 436

Text #4

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.6573. Min Act: -0.0000

Data Index: 756595 (The Pile)

Max Activating Token Index: 607

Text #5

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.6880. Min Act: -0.0000

Data Index: 502510 (The Pile)

Max Activating Token Index: 308

Text #6

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.7042. Min Act: -0.0000

Data Index: 1472609 (The Pile)

Max Activating Token Index: 60

Text #7

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.6647. Min Act: -0.0000

Data Index: 55777 (The Pile)

Max Activating Token Index: 662

Text #8

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.6841. Min Act: -0.0000

Data Index: 1984433 (The Pile)

Max Activating Token Index: 379

Text #9

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.6387. Min Act: -0.0000

Data Index: 1600079 (The Pile)

Max Activating Token Index: 328

Text #10

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.6550. Min Act: -0.0000

Data Index: 1561767 (The Pile)

Max Activating Token Index: 590

Text #11

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.6488. Min Act: -0.0000

Data Index: 549207 (The Pile)

Max Activating Token Index: 441

Text #12

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.6750. Min Act: -0.0000

Data Index: 266610 (The Pile)

Max Activating Token Index: 864

Text #13

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.6085. Min Act: -0.0000

Data Index: 470481 (The Pile)

Max Activating Token Index: 832

Text #14

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.6603. Min Act: -0.0000

Data Index: 983228 (The Pile)

Max Activating Token Index: 426

Text #15

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.6358. Min Act: -0.0000

Data Index: 1235728 (The Pile)

Max Activating Token Index: 398

Text #16

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.6475. Min Act: -0.0000

Data Index: 490257 (The Pile)

Max Activating Token Index: 1015

Text #17

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.6063. Min Act: -0.0000

Data Index: 207694 (The Pile)

Max Activating Token Index: 12

Text #18

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.5979. Min Act: -0.0000

Data Index: 1683755 (The Pile)

Max Activating Token Index: 34

Text #19

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.6791. Min Act: -0.0000

Data Index: 1758861 (The Pile)

Max Activating Token Index: 76