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

Dataset: The Pile

Neuron 4348 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: 0.6061. Min Range: -0.6061

Max Act: 0.6061. Min Act: -0.0000

Data Index: 384975 (The Pile)

Max Activating Token Index: 58

Text #1

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.5971. Min Act: -0.0000

Data Index: 1581389 (The Pile)

Max Activating Token Index: 939

Text #2

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.5837. Min Act: -0.0000

Data Index: 359747 (The Pile)

Max Activating Token Index: 366

Text #3

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.5754. Min Act: -0.0000

Data Index: 1597087 (The Pile)

Max Activating Token Index: 474

Text #4

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.5688. Min Act: -0.0000

Data Index: 636121 (The Pile)

Max Activating Token Index: 262

Text #5

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.5635. Min Act: -0.0000

Data Index: 1541165 (The Pile)

Max Activating Token Index: 846

Text #6

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.5497. Min Act: -0.0000

Data Index: 818955 (The Pile)

Max Activating Token Index: 981

Text #7

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.5573. Min Act: -0.0000

Data Index: 1711606 (The Pile)

Max Activating Token Index: 420

Text #8

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.5459. Min Act: -0.0000

Data Index: 1325782 (The Pile)

Max Activating Token Index: 463

Text #9

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.5313. Min Act: -0.0000

Data Index: 1083715 (The Pile)

Max Activating Token Index: 888

Text #10

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.5335. Min Act: -0.0000

Data Index: 1738705 (The Pile)

Max Activating Token Index: 140

Text #11

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.5147. Min Act: -0.0000

Data Index: 1419500 (The Pile)

Max Activating Token Index: 440

Text #12

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.5252. Min Act: -0.0000

Data Index: 880766 (The Pile)

Max Activating Token Index: 636

Text #13

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.5138. Min Act: -0.0000

Data Index: 1035859 (The Pile)

Max Activating Token Index: 874

Text #14

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.5089. Min Act: -0.0000

Data Index: 1522109 (The Pile)

Max Activating Token Index: 13

Text #15

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.5249. Min Act: -0.0000

Data Index: 1751892 (The Pile)

Max Activating Token Index: 3

Text #16

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.5175. Min Act: -0.0000

Data Index: 647072 (The Pile)

Max Activating Token Index: 631

Text #17

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.5172. Min Act: -0.0000

Data Index: 1833740 (The Pile)

Max Activating Token Index: 614

Text #18

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.4982. Min Act: -0.0000

Data Index: 582039 (The Pile)

Max Activating Token Index: 329

Text #19

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.5254. Min Act: -0.0000

Data Index: 1879024 (The Pile)

Max Activating Token Index: 981