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

Dataset: The Pile

Neuron 3950 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3592. Min Range: -1.3592

Max Act: 1.3503. Min Act: -0.0000

Data Index: 870242 (The Pile)

Max Activating Token Index: 875

Text #1

Max Range: 1.3592. Min Range: -1.3592

Max Act: 1.3592. Min Act: -0.0000

Data Index: 1608459 (The Pile)

Max Activating Token Index: 814

Text #2

Max Range: 1.3592. Min Range: -1.3592

Max Act: 1.2921. Min Act: -0.0000

Data Index: 685652 (The Pile)

Max Activating Token Index: 701

Text #3

Max Range: 1.3592. Min Range: -1.3592

Max Act: 1.2876. Min Act: -0.0000

Data Index: 1556935 (The Pile)

Max Activating Token Index: 30

Text #4

Max Range: 1.3592. Min Range: -1.3592

Max Act: 1.3109. Min Act: -0.0000

Data Index: 1721672 (The Pile)

Max Activating Token Index: 858

Text #5

Max Range: 1.3592. Min Range: -1.3592

Max Act: 1.3079. Min Act: -0.0000

Data Index: 1691246 (The Pile)

Max Activating Token Index: 563

Text #6

Max Range: 1.3592. Min Range: -1.3592

Max Act: 1.2661. Min Act: -0.0000

Data Index: 1862782 (The Pile)

Max Activating Token Index: 922

Text #7

Max Range: 1.3592. Min Range: -1.3592

Max Act: 1.2615. Min Act: -0.0000

Data Index: 246125 (The Pile)

Max Activating Token Index: 713

Text #8

Max Range: 1.3592. Min Range: -1.3592

Max Act: 1.2399. Min Act: -0.0000

Data Index: 1534560 (The Pile)

Max Activating Token Index: 140

Text #9

Max Range: 1.3592. Min Range: -1.3592

Max Act: 1.1883. Min Act: -0.0000

Data Index: 1726514 (The Pile)

Max Activating Token Index: 90

Text #10

Max Range: 1.3592. Min Range: -1.3592

Max Act: 1.2443. Min Act: -0.0000

Data Index: 1313670 (The Pile)

Max Activating Token Index: 928

Text #11

Max Range: 1.3592. Min Range: -1.3592

Max Act: 1.2327. Min Act: -0.0000

Data Index: 1050853 (The Pile)

Max Activating Token Index: 645

Text #12

Max Range: 1.3592. Min Range: -1.3592

Max Act: 1.3061. Min Act: -0.0000

Data Index: 1405566 (The Pile)

Max Activating Token Index: 975

Text #13

Max Range: 1.3592. Min Range: -1.3592

Max Act: 1.3064. Min Act: -0.0000

Data Index: 1007700 (The Pile)

Max Activating Token Index: 797

Text #14

Max Range: 1.3592. Min Range: -1.3592

Max Act: 1.2217. Min Act: -0.0000

Data Index: 1609079 (The Pile)

Max Activating Token Index: 103

Text #15

Max Range: 1.3592. Min Range: -1.3592

Max Act: 1.2179. Min Act: -0.0000

Data Index: 943284 (The Pile)

Max Activating Token Index: 899

Text #16

Max Range: 1.3592. Min Range: -1.3592

Max Act: 1.1907. Min Act: -0.0000

Data Index: 373959 (The Pile)

Max Activating Token Index: 10

Text #17

Max Range: 1.3592. Min Range: -1.3592

Max Act: 1.1482. Min Act: -0.0000

Data Index: 663432 (The Pile)

Max Activating Token Index: 994

Text #18

Max Range: 1.3592. Min Range: -1.3592

Max Act: 1.1494. Min Act: -0.0000

Data Index: 1885069 (The Pile)

Max Activating Token Index: 899

Text #19

Max Range: 1.3592. Min Range: -1.3592

Max Act: 1.2567. Min Act: -0.0000

Data Index: 1364542 (The Pile)

Max Activating Token Index: 729