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

Dataset: The Pile

Neuron 1666 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: 5.3567. Min Range: -5.3567

Max Act: 5.3567. Min Act: -0.0000

Data Index: 1912550 (The Pile)

Max Activating Token Index: 445

Text #1

Max Range: 5.3567. Min Range: -5.3567

Max Act: 4.8555. Min Act: -0.0000

Data Index: 217711 (The Pile)

Max Activating Token Index: 834

Text #2

Max Range: 5.3567. Min Range: -5.3567

Max Act: 5.1021. Min Act: -0.0000

Data Index: 1890976 (The Pile)

Max Activating Token Index: 469

Text #3

Max Range: 5.3567. Min Range: -5.3567

Max Act: 5.0522. Min Act: -0.0000

Data Index: 1149805 (The Pile)

Max Activating Token Index: 942

Text #4

Max Range: 5.3567. Min Range: -5.3567

Max Act: 3.8501. Min Act: -0.0000

Data Index: 81667 (The Pile)

Max Activating Token Index: 315

Text #5

Max Range: 5.3567. Min Range: -5.3567

Max Act: 3.0154. Min Act: -0.0000

Data Index: 246157 (The Pile)

Max Activating Token Index: 347

Text #6

Max Range: 5.3567. Min Range: -5.3567

Max Act: 2.6093. Min Act: -0.0000

Data Index: 545022 (The Pile)

Max Activating Token Index: 717

Text #7

Max Range: 5.3567. Min Range: -5.3567

Max Act: 2.8432. Min Act: 0.0000

Data Index: 1357143 (The Pile)

Max Activating Token Index: 352

Text #8

Max Range: 5.3567. Min Range: -5.3567

Max Act: 2.8318. Min Act: -0.0000

Data Index: 941148 (The Pile)

Max Activating Token Index: 633

Text #9

Max Range: 5.3567. Min Range: -5.3567

Max Act: 2.7969. Min Act: -0.0000

Data Index: 158422 (The Pile)

Max Activating Token Index: 209

Text #10

Max Range: 5.3567. Min Range: -5.3567

Max Act: 2.5357. Min Act: -0.0000

Data Index: 1104729 (The Pile)

Max Activating Token Index: 240

Text #11

Max Range: 5.3567. Min Range: -5.3567

Max Act: 2.4302. Min Act: -0.0000

Data Index: 1107455 (The Pile)

Max Activating Token Index: 138

Text #12

Max Range: 5.3567. Min Range: -5.3567

Max Act: 2.4779. Min Act: -0.0000

Data Index: 978988 (The Pile)

Max Activating Token Index: 760

Text #13

Max Range: 5.3567. Min Range: -5.3567

Max Act: 2.1735. Min Act: -0.0000

Data Index: 1178327 (The Pile)

Max Activating Token Index: 670

Text #14

Max Range: 5.3567. Min Range: -5.3567

Max Act: 2.2635. Min Act: -0.0000

Data Index: 367748 (The Pile)

Max Activating Token Index: 505

Text #15

Max Range: 5.3567. Min Range: -5.3567

Max Act: 2.2191. Min Act: -0.0000

Data Index: 1646583 (The Pile)

Max Activating Token Index: 467

Text #16

Max Range: 5.3567. Min Range: -5.3567

Max Act: 2.3370. Min Act: -0.0000

Data Index: 252556 (The Pile)

Max Activating Token Index: 357

Text #17

Max Range: 5.3567. Min Range: -5.3567

Max Act: 1.9072. Min Act: -0.0000

Data Index: 559502 (The Pile)

Max Activating Token Index: 89

Text #18

Max Range: 5.3567. Min Range: -5.3567

Max Act: 2.1910. Min Act: -0.0000

Data Index: 1904272 (The Pile)

Max Activating Token Index: 543

Text #19

Max Range: 5.3567. Min Range: -5.3567

Max Act: 2.0262. Min Act: -0.0000

Data Index: 1195320 (The Pile)

Max Activating Token Index: 94