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

Dataset: The Pile

Neuron 1138 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: 1.3664. Min Range: -1.3664

Max Act: 1.3664. Min Act: -0.0000

Data Index: 366875 (The Pile)

Max Activating Token Index: 185

Text #1

Max Range: 1.3664. Min Range: -1.3664

Max Act: 1.2111. Min Act: -0.0000

Data Index: 853653 (The Pile)

Max Activating Token Index: 227

Text #2

Max Range: 1.3664. Min Range: -1.3664

Max Act: 1.0932. Min Act: -0.0000

Data Index: 107717 (The Pile)

Max Activating Token Index: 632

Text #3

Max Range: 1.3664. Min Range: -1.3664

Max Act: 1.1666. Min Act: -0.0000

Data Index: 1579874 (The Pile)

Max Activating Token Index: 374

Text #4

Max Range: 1.3664. Min Range: -1.3664

Max Act: 1.0652. Min Act: -0.0000

Data Index: 399120 (The Pile)

Max Activating Token Index: 688

Text #5

Max Range: 1.3664. Min Range: -1.3664

Max Act: 1.0773. Min Act: -0.0000

Data Index: 283525 (The Pile)

Max Activating Token Index: 617

Text #6

Max Range: 1.3664. Min Range: -1.3664

Max Act: 1.1063. Min Act: -0.0000

Data Index: 1481806 (The Pile)

Max Activating Token Index: 270

Text #7

Max Range: 1.3664. Min Range: -1.3664

Max Act: 1.1109. Min Act: -0.0000

Data Index: 1903041 (The Pile)

Max Activating Token Index: 957

Text #8

Max Range: 1.3664. Min Range: -1.3664

Max Act: 1.1007. Min Act: -0.0000

Data Index: 279977 (The Pile)

Max Activating Token Index: 670

Text #9

Max Range: 1.3664. Min Range: -1.3664

Max Act: 1.1253. Min Act: -0.0000

Data Index: 52381 (The Pile)

Max Activating Token Index: 318

Text #10

Max Range: 1.3664. Min Range: -1.3664

Max Act: 1.0922. Min Act: -0.0000

Data Index: 1176428 (The Pile)

Max Activating Token Index: 779

Text #11

Max Range: 1.3664. Min Range: -1.3664

Max Act: 1.0341. Min Act: -0.0000

Data Index: 1529460 (The Pile)

Max Activating Token Index: 21

Text #12

Max Range: 1.3664. Min Range: -1.3664

Max Act: 1.1366. Min Act: -0.0000

Data Index: 1128259 (The Pile)

Max Activating Token Index: 264

Text #13

Max Range: 1.3664. Min Range: -1.3664

Max Act: 0.9137. Min Act: -0.0000

Data Index: 148209 (The Pile)

Max Activating Token Index: 724

Text #14

Max Range: 1.3664. Min Range: -1.3664

Max Act: 1.0133. Min Act: -0.0000

Data Index: 1592879 (The Pile)

Max Activating Token Index: 164

Text #15

Max Range: 1.3664. Min Range: -1.3664

Max Act: 0.9758. Min Act: -0.0000

Data Index: 1400677 (The Pile)

Max Activating Token Index: 391

Text #16

Max Range: 1.3664. Min Range: -1.3664

Max Act: 0.9593. Min Act: -0.0000

Data Index: 900915 (The Pile)

Max Activating Token Index: 60

Text #17

Max Range: 1.3664. Min Range: -1.3664

Max Act: 1.0479. Min Act: -0.0000

Data Index: 1754724 (The Pile)

Max Activating Token Index: 319

Text #18

Max Range: 1.3664. Min Range: -1.3664

Max Act: 0.9807. Min Act: -0.0000

Data Index: 1154175 (The Pile)

Max Activating Token Index: 155

Text #19

Max Range: 1.3664. Min Range: -1.3664

Max Act: 0.9781. Min Act: -0.0000

Data Index: 1966787 (The Pile)

Max Activating Token Index: 352