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

Dataset: The Pile

Neuron 859 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.7592. Min Range: -0.7592

Max Act: 0.7516. Min Act: -0.0000

Data Index: 11910 (The Pile)

Max Activating Token Index: 973

Text #1

Max Range: 0.7592. Min Range: -0.7592

Max Act: 0.7332. Min Act: -0.0000

Data Index: 1385952 (The Pile)

Max Activating Token Index: 1019

Text #2

Max Range: 0.7592. Min Range: -0.7592

Max Act: 0.7136. Min Act: -0.0000

Data Index: 1033853 (The Pile)

Max Activating Token Index: 981

Text #3

Max Range: 0.7592. Min Range: -0.7592

Max Act: 0.7567. Min Act: -0.0000

Data Index: 1827107 (The Pile)

Max Activating Token Index: 414

Text #4

Max Range: 0.7592. Min Range: -0.7592

Max Act: 0.7592. Min Act: -0.0000

Data Index: 959052 (The Pile)

Max Activating Token Index: 829

Text #5

Max Range: 0.7592. Min Range: -0.7592

Max Act: 0.7571. Min Act: -0.0000

Data Index: 526039 (The Pile)

Max Activating Token Index: 400

Text #6

Max Range: 0.7592. Min Range: -0.7592

Max Act: 0.7541. Min Act: -0.0000

Data Index: 1358195 (The Pile)

Max Activating Token Index: 530

Text #7

Max Range: 0.7592. Min Range: -0.7592

Max Act: 0.7426. Min Act: 0.0000

Data Index: 1113188 (The Pile)

Max Activating Token Index: 969

Text #8

Max Range: 0.7592. Min Range: -0.7592

Max Act: 0.6812. Min Act: -0.0000

Data Index: 1323160 (The Pile)

Max Activating Token Index: 153

Text #9

Max Range: 0.7592. Min Range: -0.7592

Max Act: 0.6691. Min Act: -0.0000

Data Index: 801287 (The Pile)

Max Activating Token Index: 753

Text #10

Max Range: 0.7592. Min Range: -0.7592

Max Act: 0.6565. Min Act: -0.0000

Data Index: 385056 (The Pile)

Max Activating Token Index: 153

Text #11

Max Range: 0.7592. Min Range: -0.7592

Max Act: 0.6779. Min Act: -0.0000

Data Index: 1904748 (The Pile)

Max Activating Token Index: 756

Text #12

Max Range: 0.7592. Min Range: -0.7592

Max Act: 0.7462. Min Act: -0.0000

Data Index: 1635977 (The Pile)

Max Activating Token Index: 302

Text #13

Max Range: 0.7592. Min Range: -0.7592

Max Act: 0.6570. Min Act: -0.0000

Data Index: 1667272 (The Pile)

Max Activating Token Index: 1007

Text #14

Max Range: 0.7592. Min Range: -0.7592

Max Act: 0.7139. Min Act: -0.0000

Data Index: 1283969 (The Pile)

Max Activating Token Index: 646

Text #15

Max Range: 0.7592. Min Range: -0.7592

Max Act: 0.6925. Min Act: -0.0000

Data Index: 1803180 (The Pile)

Max Activating Token Index: 995

Text #16

Max Range: 0.7592. Min Range: -0.7592

Max Act: 0.6898. Min Act: -0.0000

Data Index: 1531351 (The Pile)

Max Activating Token Index: 432

Text #17

Max Range: 0.7592. Min Range: -0.7592

Max Act: 0.6661. Min Act: -0.0000

Data Index: 139051 (The Pile)

Max Activating Token Index: 614

Text #18

Max Range: 0.7592. Min Range: -0.7592

Max Act: 0.6858. Min Act: -0.0000

Data Index: 1418362 (The Pile)

Max Activating Token Index: 878

Text #19

Max Range: 0.7592. Min Range: -0.7592

Max Act: 0.6842. Min Act: -0.0000

Data Index: 72585 (The Pile)

Max Activating Token Index: 135