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

Dataset: The Pile

Neuron 3293 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.8351. Min Act: -0.0000

Data Index: 142406 (The Pile)

Max Activating Token Index: 973

Text #1

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.7133. Min Act: -0.0000

Data Index: 1131357 (The Pile)

Max Activating Token Index: 982

Text #2

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.8932. Min Act: -0.0000

Data Index: 1545330 (The Pile)

Max Activating Token Index: 1014

Text #3

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.6949. Min Act: -0.0000

Data Index: 862592 (The Pile)

Max Activating Token Index: 977

Text #4

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.8146. Min Act: -0.0000

Data Index: 1968389 (The Pile)

Max Activating Token Index: 435

Text #5

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.7568. Min Act: -0.0000

Data Index: 1849935 (The Pile)

Max Activating Token Index: 739

Text #6

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.8645. Min Act: -0.0000

Data Index: 1069739 (The Pile)

Max Activating Token Index: 951

Text #7

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.7788. Min Act: -0.0000

Data Index: 66345 (The Pile)

Max Activating Token Index: 995

Text #8

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.7316. Min Act: -0.0000

Data Index: 1415483 (The Pile)

Max Activating Token Index: 728

Text #9

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.6294. Min Act: -0.0000

Data Index: 1340160 (The Pile)

Max Activating Token Index: 848

Text #10

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.6933. Min Act: 0.0000

Data Index: 633090 (The Pile)

Max Activating Token Index: 694

Text #11

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.5666. Min Act: -0.0000

Data Index: 122598 (The Pile)

Max Activating Token Index: 1003

Text #12

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.5862. Min Act: -0.0000

Data Index: 157744 (The Pile)

Max Activating Token Index: 326

Text #13

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.6612. Min Act: -0.0000

Data Index: 1748959 (The Pile)

Max Activating Token Index: 749

Text #14

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.6843. Min Act: -0.0000

Data Index: 1155403 (The Pile)

Max Activating Token Index: 511

Text #15

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.6804. Min Act: -0.0000

Data Index: 1522575 (The Pile)

Max Activating Token Index: 63

Text #16

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.6822. Min Act: -0.0000

Data Index: 1846087 (The Pile)

Max Activating Token Index: 540

Text #17

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.7148. Min Act: -0.0000

Data Index: 1219613 (The Pile)

Max Activating Token Index: 64

Text #18

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.6480. Min Act: -0.0000

Data Index: 311264 (The Pile)

Max Activating Token Index: 383

Text #19

Max Range: 0.8932. Min Range: -0.8932

Max Act: 0.6319. Min Act: -0.0000

Data Index: 1557298 (The Pile)

Max Activating Token Index: 628