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

Dataset: The Pile

Neuron 3660 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: 0.9096. Min Range: -0.9096

Max Act: 0.9096. Min Act: -0.0000

Data Index: 276071 (The Pile)

Max Activating Token Index: 728

Text #1

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.7986. Min Act: -0.0000

Data Index: 794038 (The Pile)

Max Activating Token Index: 622

Text #2

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.7727. Min Act: -0.0000

Data Index: 185253 (The Pile)

Max Activating Token Index: 41

Text #3

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.7694. Min Act: -0.0000

Data Index: 869596 (The Pile)

Max Activating Token Index: 955

Text #4

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.7449. Min Act: -0.0000

Data Index: 525144 (The Pile)

Max Activating Token Index: 814

Text #5

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.7402. Min Act: -0.0000

Data Index: 606918 (The Pile)

Max Activating Token Index: 213

Text #6

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.7406. Min Act: -0.0000

Data Index: 502038 (The Pile)

Max Activating Token Index: 65

Text #7

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.7152. Min Act: -0.0000

Data Index: 1124206 (The Pile)

Max Activating Token Index: 505

Text #8

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.6769. Min Act: -0.0000

Data Index: 190993 (The Pile)

Max Activating Token Index: 324

Text #9

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.6701. Min Act: -0.0000

Data Index: 1870860 (The Pile)

Max Activating Token Index: 123

Text #10

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.6783. Min Act: -0.0000

Data Index: 537239 (The Pile)

Max Activating Token Index: 923

Text #11

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.7311. Min Act: -0.0000

Data Index: 1431523 (The Pile)

Max Activating Token Index: 649

Text #12

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.6560. Min Act: -0.0000

Data Index: 945686 (The Pile)

Max Activating Token Index: 444

Text #13

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.6684. Min Act: -0.0000

Data Index: 1588164 (The Pile)

Max Activating Token Index: 872

Text #14

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.6490. Min Act: -0.0000

Data Index: 1650225 (The Pile)

Max Activating Token Index: 722

Text #15

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.6448. Min Act: -0.0000

Data Index: 2071 (The Pile)

Max Activating Token Index: 272

Text #16

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.6626. Min Act: -0.0000

Data Index: 456131 (The Pile)

Max Activating Token Index: 384

Text #17

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.6453. Min Act: -0.0000

Data Index: 1065758 (The Pile)

Max Activating Token Index: 965

Text #18

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.6600. Min Act: -0.0000

Data Index: 845397 (The Pile)

Max Activating Token Index: 912

Text #19

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.6349. Min Act: -0.0000

Data Index: 1051275 (The Pile)

Max Activating Token Index: 147