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

Dataset: The Pile

Neuron 3812 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3393. Min Range: -1.3393

Max Act: 1.3393. Min Act: -0.0000

Data Index: 1555250 (The Pile)

Max Activating Token Index: 897

Text #1

Max Range: 1.3393. Min Range: -1.3393

Max Act: 1.1974. Min Act: -0.0000

Data Index: 1897310 (The Pile)

Max Activating Token Index: 776

Text #2

Max Range: 1.3393. Min Range: -1.3393

Max Act: 1.1651. Min Act: -0.0000

Data Index: 1145054 (The Pile)

Max Activating Token Index: 889

Text #3

Max Range: 1.3393. Min Range: -1.3393

Max Act: 1.0848. Min Act: -0.0000

Data Index: 1059272 (The Pile)

Max Activating Token Index: 999

Text #4

Max Range: 1.3393. Min Range: -1.3393

Max Act: 1.0533. Min Act: -0.0000

Data Index: 838894 (The Pile)

Max Activating Token Index: 481

Text #5

Max Range: 1.3393. Min Range: -1.3393

Max Act: 1.0809. Min Act: -0.0000

Data Index: 972124 (The Pile)

Max Activating Token Index: 614

Text #6

Max Range: 1.3393. Min Range: -1.3393

Max Act: 1.0537. Min Act: -0.0000

Data Index: 414879 (The Pile)

Max Activating Token Index: 403

Text #7

Max Range: 1.3393. Min Range: -1.3393

Max Act: 1.0434. Min Act: -0.0000

Data Index: 572151 (The Pile)

Max Activating Token Index: 145

Text #8

Max Range: 1.3393. Min Range: -1.3393

Max Act: 1.0075. Min Act: -0.0000

Data Index: 111913 (The Pile)

Max Activating Token Index: 635

Text #9

Max Range: 1.3393. Min Range: -1.3393

Max Act: 0.9391. Min Act: -0.0000

Data Index: 1057329 (The Pile)

Max Activating Token Index: 348

Text #10

Max Range: 1.3393. Min Range: -1.3393

Max Act: 1.0292. Min Act: -0.0000

Data Index: 724782 (The Pile)

Max Activating Token Index: 633

Text #11

Max Range: 1.3393. Min Range: -1.3393

Max Act: 1.0874. Min Act: -0.0000

Data Index: 1701702 (The Pile)

Max Activating Token Index: 37

Text #12

Max Range: 1.3393. Min Range: -1.3393

Max Act: 0.9596. Min Act: -0.0000

Data Index: 655891 (The Pile)

Max Activating Token Index: 283

Text #13

Max Range: 1.3393. Min Range: -1.3393

Max Act: 0.9915. Min Act: -0.0000

Data Index: 130858 (The Pile)

Max Activating Token Index: 121

Text #14

Max Range: 1.3393. Min Range: -1.3393

Max Act: 0.9208. Min Act: -0.0000

Data Index: 1311483 (The Pile)

Max Activating Token Index: 733

Text #15

Max Range: 1.3393. Min Range: -1.3393

Max Act: 0.9163. Min Act: -0.0000

Data Index: 515916 (The Pile)

Max Activating Token Index: 442

Text #16

Max Range: 1.3393. Min Range: -1.3393

Max Act: 0.9312. Min Act: -0.0000

Data Index: 1589382 (The Pile)

Max Activating Token Index: 120

Text #17

Max Range: 1.3393. Min Range: -1.3393

Max Act: 0.9026. Min Act: -0.0000

Data Index: 1603230 (The Pile)

Max Activating Token Index: 1010

Text #18

Max Range: 1.3393. Min Range: -1.3393

Max Act: 0.9446. Min Act: -0.0000

Data Index: 773998 (The Pile)

Max Activating Token Index: 131

Text #19

Max Range: 1.3393. Min Range: -1.3393

Max Act: 0.9129. Min Act: -0.0000

Data Index: 1550042 (The Pile)

Max Activating Token Index: 118