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

Dataset: The Pile

Neuron 4783 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7886. Min Range: -3.7886

Max Act: 3.7126. Min Act: -0.0000

Data Index: 126911 (The Pile)

Max Activating Token Index: 995

Text #1

Max Range: 3.7886. Min Range: -3.7886

Max Act: 3.7886. Min Act: -0.0000

Data Index: 1021984 (The Pile)

Max Activating Token Index: 37

Text #2

Max Range: 3.7886. Min Range: -3.7886

Max Act: 3.5494. Min Act: -0.0000

Data Index: 1971793 (The Pile)

Max Activating Token Index: 969

Text #3

Max Range: 3.7886. Min Range: -3.7886

Max Act: 3.6378. Min Act: -0.0000

Data Index: 1279134 (The Pile)

Max Activating Token Index: 879

Text #4

Max Range: 3.7886. Min Range: -3.7886

Max Act: 3.5016. Min Act: -0.0000

Data Index: 640441 (The Pile)

Max Activating Token Index: 614

Text #5

Max Range: 3.7886. Min Range: -3.7886

Max Act: 3.2751. Min Act: -0.0000

Data Index: 1463511 (The Pile)

Max Activating Token Index: 751

Text #6

Max Range: 3.7886. Min Range: -3.7886

Max Act: 3.4345. Min Act: -0.0000

Data Index: 1576900 (The Pile)

Max Activating Token Index: 449

Text #7

Max Range: 3.7886. Min Range: -3.7886

Max Act: 3.5590. Min Act: -0.0000

Data Index: 1208375 (The Pile)

Max Activating Token Index: 611

Text #8

Max Range: 3.7886. Min Range: -3.7886

Max Act: 3.2055. Min Act: -0.0000

Data Index: 1213057 (The Pile)

Max Activating Token Index: 482

Text #9

Max Range: 3.7886. Min Range: -3.7886

Max Act: 3.3051. Min Act: -0.0000

Data Index: 1271233 (The Pile)

Max Activating Token Index: 684

Text #10

Max Range: 3.7886. Min Range: -3.7886

Max Act: 3.4477. Min Act: -0.0000

Data Index: 853609 (The Pile)

Max Activating Token Index: 72

Text #11

Max Range: 3.7886. Min Range: -3.7886

Max Act: 3.2542. Min Act: -0.0000

Data Index: 261081 (The Pile)

Max Activating Token Index: 217

Text #12

Max Range: 3.7886. Min Range: -3.7886

Max Act: 3.3570. Min Act: -0.0000

Data Index: 35417 (The Pile)

Max Activating Token Index: 478

Text #13

Max Range: 3.7886. Min Range: -3.7886

Max Act: 3.1877. Min Act: -0.0000

Data Index: 454392 (The Pile)

Max Activating Token Index: 304

Text #14

Max Range: 3.7886. Min Range: -3.7886

Max Act: 3.0440. Min Act: -0.0000

Data Index: 1696019 (The Pile)

Max Activating Token Index: 299

Text #15

Max Range: 3.7886. Min Range: -3.7886

Max Act: 3.3062. Min Act: -0.0000

Data Index: 1472645 (The Pile)

Max Activating Token Index: 975

Text #16

Max Range: 3.7886. Min Range: -3.7886

Max Act: 3.0052. Min Act: -0.0000

Data Index: 1452128 (The Pile)

Max Activating Token Index: 407

Text #17

Max Range: 3.7886. Min Range: -3.7886

Max Act: 2.9946. Min Act: -0.0000

Data Index: 1121975 (The Pile)

Max Activating Token Index: 887

Text #18

Max Range: 3.7886. Min Range: -3.7886

Max Act: 3.2816. Min Act: -0.0000

Data Index: 6704 (The Pile)

Max Activating Token Index: 969

Text #19

Max Range: 3.7886. Min Range: -3.7886

Max Act: 3.1237. Min Act: -0.0000

Data Index: 239922 (The Pile)

Max Activating Token Index: 525