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

Dataset: The Pile

Neuron 4041 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: 0.2455. Min Range: -0.2455

Max Act: 0.2421. Min Act: 0.0000

Data Index: 1241024 (The Pile)

Max Activating Token Index: 641

Text #1

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.2412. Min Act: -0.0000

Data Index: 1930099 (The Pile)

Max Activating Token Index: 15

Text #2

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.2455. Min Act: -0.0000

Data Index: 1646707 (The Pile)

Max Activating Token Index: 536

Text #3

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.2279. Min Act: 0.0000

Data Index: 1010601 (The Pile)

Max Activating Token Index: 471

Text #4

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.2255. Min Act: 0.0000

Data Index: 668444 (The Pile)

Max Activating Token Index: 939

Text #5

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.2101. Min Act: -0.0000

Data Index: 1731446 (The Pile)

Max Activating Token Index: 409

Text #6

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.2080. Min Act: -0.0000

Data Index: 300959 (The Pile)

Max Activating Token Index: 733

Text #7

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.2026. Min Act: -0.0000

Data Index: 835551 (The Pile)

Max Activating Token Index: 649

Text #8

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.1974. Min Act: -0.0000

Data Index: 639352 (The Pile)

Max Activating Token Index: 499

Text #9

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.1864. Min Act: -0.0000

Data Index: 643669 (The Pile)

Max Activating Token Index: 989

Text #10

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.1960. Min Act: -0.0000

Data Index: 363827 (The Pile)

Max Activating Token Index: 224

Text #11

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.1932. Min Act: -0.0000

Data Index: 347363 (The Pile)

Max Activating Token Index: 463

Text #12

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.1751. Min Act: -0.0000

Data Index: 1106109 (The Pile)

Max Activating Token Index: 523

Text #13

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.1848. Min Act: -0.0000

Data Index: 820837 (The Pile)

Max Activating Token Index: 805

Text #14

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.1848. Min Act: -0.0000

Data Index: 1541003 (The Pile)

Max Activating Token Index: 100

Text #15

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.1776. Min Act: -0.0000

Data Index: 202627 (The Pile)

Max Activating Token Index: 35

Text #16

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.1939. Min Act: -0.0000

Data Index: 432464 (The Pile)

Max Activating Token Index: 76

Text #17

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.1780. Min Act: 0.0000

Data Index: 1898438 (The Pile)

Max Activating Token Index: 989

Text #18

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.1857. Min Act: -0.0000

Data Index: 929842 (The Pile)

Max Activating Token Index: 596

Text #19

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.1718. Min Act: -0.0000

Data Index: 1994942 (The Pile)

Max Activating Token Index: 531