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

Dataset: The Pile

Neuron 1945 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1752. Min Range: -1.1752

Max Act: 1.1752. Min Act: -0.0000

Data Index: 1006382 (The Pile)

Max Activating Token Index: 440

Text #1

Max Range: 1.1752. Min Range: -1.1752

Max Act: 0.9472. Min Act: -0.0000

Data Index: 1019466 (The Pile)

Max Activating Token Index: 467

Text #2

Max Range: 1.1752. Min Range: -1.1752

Max Act: 0.9721. Min Act: -0.0000

Data Index: 66565 (The Pile)

Max Activating Token Index: 146

Text #3

Max Range: 1.1752. Min Range: -1.1752

Max Act: 1.0399. Min Act: -0.0000

Data Index: 1264553 (The Pile)

Max Activating Token Index: 679

Text #4

Max Range: 1.1752. Min Range: -1.1752

Max Act: 0.9233. Min Act: -0.0000

Data Index: 1195741 (The Pile)

Max Activating Token Index: 494

Text #5

Max Range: 1.1752. Min Range: -1.1752

Max Act: 0.8955. Min Act: -0.0000

Data Index: 1928784 (The Pile)

Max Activating Token Index: 607

Text #6

Max Range: 1.1752. Min Range: -1.1752

Max Act: 0.8738. Min Act: -0.0000

Data Index: 706563 (The Pile)

Max Activating Token Index: 227

Text #7

Max Range: 1.1752. Min Range: -1.1752

Max Act: 1.0045. Min Act: 0.0000

Data Index: 883833 (The Pile)

Max Activating Token Index: 824

Text #8

Max Range: 1.1752. Min Range: -1.1752

Max Act: 0.8587. Min Act: -0.0000

Data Index: 906807 (The Pile)

Max Activating Token Index: 361

Text #9

Max Range: 1.1752. Min Range: -1.1752

Max Act: 0.9153. Min Act: -0.0000

Data Index: 1925023 (The Pile)

Max Activating Token Index: 375

Text #10

Max Range: 1.1752. Min Range: -1.1752

Max Act: 0.9237. Min Act: -0.0000

Data Index: 1979218 (The Pile)

Max Activating Token Index: 684

Text #11

Max Range: 1.1752. Min Range: -1.1752

Max Act: 0.8922. Min Act: -0.0000

Data Index: 1273685 (The Pile)

Max Activating Token Index: 437

Text #12

Max Range: 1.1752. Min Range: -1.1752

Max Act: 0.7409. Min Act: -0.0000

Data Index: 1111042 (The Pile)

Max Activating Token Index: 603

Text #13

Max Range: 1.1752. Min Range: -1.1752

Max Act: 0.7927. Min Act: -0.0000

Data Index: 1794438 (The Pile)

Max Activating Token Index: 584

Text #14

Max Range: 1.1752. Min Range: -1.1752

Max Act: 0.8675. Min Act: -0.0000

Data Index: 538166 (The Pile)

Max Activating Token Index: 619

Text #15

Max Range: 1.1752. Min Range: -1.1752

Max Act: 0.7871. Min Act: -0.0000

Data Index: 202974 (The Pile)

Max Activating Token Index: 534

Text #16

Max Range: 1.1752. Min Range: -1.1752

Max Act: 0.7915. Min Act: -0.0000

Data Index: 580346 (The Pile)

Max Activating Token Index: 747

Text #17

Max Range: 1.1752. Min Range: -1.1752

Max Act: 0.8468. Min Act: -0.0000

Data Index: 1446943 (The Pile)

Max Activating Token Index: 658

Text #18

Max Range: 1.1752. Min Range: -1.1752

Max Act: 0.8457. Min Act: -0.0000

Data Index: 1187796 (The Pile)

Max Activating Token Index: 295

Text #19

Max Range: 1.1752. Min Range: -1.1752

Max Act: 0.8545. Min Act: -0.0000

Data Index: 133329 (The Pile)

Max Activating Token Index: 502