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

Dataset: The Pile

Neuron 723 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8175. Min Range: -0.8175

Max Act: 0.8175. Min Act: -0.0000

Data Index: 1932499 (The Pile)

Max Activating Token Index: 473

Text #1

Max Range: 0.8175. Min Range: -0.8175

Max Act: 0.7257. Min Act: -0.0000

Data Index: 493645 (The Pile)

Max Activating Token Index: 420

Text #2

Max Range: 0.8175. Min Range: -0.8175

Max Act: 0.6333. Min Act: -0.0000

Data Index: 945029 (The Pile)

Max Activating Token Index: 729

Text #3

Max Range: 0.8175. Min Range: -0.8175

Max Act: 0.6352. Min Act: -0.0000

Data Index: 596264 (The Pile)

Max Activating Token Index: 136

Text #4

Max Range: 0.8175. Min Range: -0.8175

Max Act: 0.5819. Min Act: -0.0000

Data Index: 1060012 (The Pile)

Max Activating Token Index: 31

Text #5

Max Range: 0.8175. Min Range: -0.8175

Max Act: 0.5810. Min Act: -0.0000

Data Index: 547533 (The Pile)

Max Activating Token Index: 297

Text #6

Max Range: 0.8175. Min Range: -0.8175

Max Act: 0.5359. Min Act: -0.0000

Data Index: 923720 (The Pile)

Max Activating Token Index: 401

Text #7

Max Range: 0.8175. Min Range: -0.8175

Max Act: 0.4784. Min Act: -0.0000

Data Index: 383155 (The Pile)

Max Activating Token Index: 901

Text #8

Max Range: 0.8175. Min Range: -0.8175

Max Act: 0.4763. Min Act: -0.0000

Data Index: 29192 (The Pile)

Max Activating Token Index: 481

Text #9

Max Range: 0.8175. Min Range: -0.8175

Max Act: 0.5364. Min Act: -0.0000

Data Index: 1696870 (The Pile)

Max Activating Token Index: 941

Text #10

Max Range: 0.8175. Min Range: -0.8175

Max Act: 0.5097. Min Act: -0.0000

Data Index: 132592 (The Pile)

Max Activating Token Index: 123

Text #11

Max Range: 0.8175. Min Range: -0.8175

Max Act: 0.4913. Min Act: -0.0000

Data Index: 1253626 (The Pile)

Max Activating Token Index: 441

Text #12

Max Range: 0.8175. Min Range: -0.8175

Max Act: 0.5115. Min Act: 0.0000

Data Index: 66652 (The Pile)

Max Activating Token Index: 460

Text #13

Max Range: 0.8175. Min Range: -0.8175

Max Act: 0.4827. Min Act: -0.0000

Data Index: 225441 (The Pile)

Max Activating Token Index: 718

Text #14

Max Range: 0.8175. Min Range: -0.8175

Max Act: 0.4568. Min Act: -0.0000

Data Index: 930946 (The Pile)

Max Activating Token Index: 742

Text #15

Max Range: 0.8175. Min Range: -0.8175

Max Act: 0.5349. Min Act: 0.0000

Data Index: 1353029 (The Pile)

Max Activating Token Index: 645

Text #16

Max Range: 0.8175. Min Range: -0.8175

Max Act: 0.4804. Min Act: -0.0000

Data Index: 447179 (The Pile)

Max Activating Token Index: 439

Text #17

Max Range: 0.8175. Min Range: -0.8175

Max Act: 0.4542. Min Act: -0.0000

Data Index: 194668 (The Pile)

Max Activating Token Index: 1007

Text #18

Max Range: 0.8175. Min Range: -0.8175

Max Act: 0.4641. Min Act: -0.0000

Data Index: 1482181 (The Pile)

Max Activating Token Index: 301

Text #19

Max Range: 0.8175. Min Range: -0.8175

Max Act: 0.4759. Min Act: -0.0000

Data Index: 696273 (The Pile)

Max Activating Token Index: 165