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

Dataset: The Pile

Neuron 2275 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: 0.4617. Min Range: -0.4617

Max Act: 0.4617. Min Act: -0.0000

Data Index: 1612804 (The Pile)

Max Activating Token Index: 384

Text #1

Max Range: 0.4617. Min Range: -0.4617

Max Act: 0.4334. Min Act: -0.0000

Data Index: 1151053 (The Pile)

Max Activating Token Index: 269

Text #2

Max Range: 0.4617. Min Range: -0.4617

Max Act: 0.4327. Min Act: -0.0000

Data Index: 432066 (The Pile)

Max Activating Token Index: 318

Text #3

Max Range: 0.4617. Min Range: -0.4617

Max Act: 0.4566. Min Act: -0.0000

Data Index: 1695641 (The Pile)

Max Activating Token Index: 764

Text #4

Max Range: 0.4617. Min Range: -0.4617

Max Act: 0.4058. Min Act: -0.0000

Data Index: 1855615 (The Pile)

Max Activating Token Index: 813

Text #5

Max Range: 0.4617. Min Range: -0.4617

Max Act: 0.3764. Min Act: -0.0000

Data Index: 1263845 (The Pile)

Max Activating Token Index: 332

Text #6

Max Range: 0.4617. Min Range: -0.4617

Max Act: 0.3593. Min Act: -0.0000

Data Index: 899311 (The Pile)

Max Activating Token Index: 61

Text #7

Max Range: 0.4617. Min Range: -0.4617

Max Act: 0.3305. Min Act: -0.0000

Data Index: 121979 (The Pile)

Max Activating Token Index: 753

Text #8

Max Range: 0.4617. Min Range: -0.4617

Max Act: 0.3546. Min Act: -0.0000

Data Index: 1180566 (The Pile)

Max Activating Token Index: 651

Text #9

Max Range: 0.4617. Min Range: -0.4617

Max Act: 0.3456. Min Act: -0.0000

Data Index: 1421795 (The Pile)

Max Activating Token Index: 871

Text #10

Max Range: 0.4617. Min Range: -0.4617

Max Act: 0.3498. Min Act: -0.0000

Data Index: 279029 (The Pile)

Max Activating Token Index: 1007

Text #11

Max Range: 0.4617. Min Range: -0.4617

Max Act: 0.3306. Min Act: -0.0000

Data Index: 563393 (The Pile)

Max Activating Token Index: 154

Text #12

Max Range: 0.4617. Min Range: -0.4617

Max Act: 0.3206. Min Act: -0.0000

Data Index: 998443 (The Pile)

Max Activating Token Index: 89

Text #13

Max Range: 0.4617. Min Range: -0.4617

Max Act: 0.3000. Min Act: 0.0000

Data Index: 738274 (The Pile)

Max Activating Token Index: 210

Text #14

Max Range: 0.4617. Min Range: -0.4617

Max Act: 0.3153. Min Act: -0.0000

Data Index: 274484 (The Pile)

Max Activating Token Index: 62

Text #15

Max Range: 0.4617. Min Range: -0.4617

Max Act: 0.3209. Min Act: -0.0000

Data Index: 26562 (The Pile)

Max Activating Token Index: 387

Text #16

Max Range: 0.4617. Min Range: -0.4617

Max Act: 0.3051. Min Act: -0.0000

Data Index: 1346358 (The Pile)

Max Activating Token Index: 285

Text #17

Max Range: 0.4617. Min Range: -0.4617

Max Act: 0.3218. Min Act: -0.0000

Data Index: 1839384 (The Pile)

Max Activating Token Index: 52

Text #18

Max Range: 0.4617. Min Range: -0.4617

Max Act: 0.2878. Min Act: -0.0000

Data Index: 1725750 (The Pile)

Max Activating Token Index: 939

Text #19

Max Range: 0.4617. Min Range: -0.4617

Max Act: 0.2996. Min Act: -0.0000

Data Index: 288747 (The Pile)

Max Activating Token Index: 785