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

Dataset: The Pile

Neuron 2740 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.5000. Min Act: -0.0000

Data Index: 73054 (The Pile)

Max Activating Token Index: 1006

Text #1

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.4368. Min Act: -0.0000

Data Index: 1913345 (The Pile)

Max Activating Token Index: 739

Text #2

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.3786. Min Act: -0.0000

Data Index: 1442709 (The Pile)

Max Activating Token Index: 761

Text #3

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.3134. Min Act: -0.0000

Data Index: 671348 (The Pile)

Max Activating Token Index: 956

Text #4

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.2847. Min Act: -0.0000

Data Index: 848346 (The Pile)

Max Activating Token Index: 938

Text #5

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.2810. Min Act: -0.0000

Data Index: 1900032 (The Pile)

Max Activating Token Index: 952

Text #6

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.2848. Min Act: -0.0000

Data Index: 1003805 (The Pile)

Max Activating Token Index: 299

Text #7

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.2839. Min Act: -0.0000

Data Index: 1310163 (The Pile)

Max Activating Token Index: 999

Text #8

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.2616. Min Act: -0.0000

Data Index: 24063 (The Pile)

Max Activating Token Index: 160

Text #9

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.2794. Min Act: -0.0000

Data Index: 700515 (The Pile)

Max Activating Token Index: 910

Text #10

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.2933. Min Act: -0.0000

Data Index: 167108 (The Pile)

Max Activating Token Index: 944

Text #11

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.2987. Min Act: -0.0000

Data Index: 1859655 (The Pile)

Max Activating Token Index: 917

Text #12

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.2428. Min Act: -0.0000

Data Index: 1212099 (The Pile)

Max Activating Token Index: 337

Text #13

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.2258. Min Act: -0.0000

Data Index: 1105414 (The Pile)

Max Activating Token Index: 650

Text #14

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.2620. Min Act: -0.0000

Data Index: 310903 (The Pile)

Max Activating Token Index: 426

Text #15

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.2405. Min Act: -0.0000

Data Index: 1294828 (The Pile)

Max Activating Token Index: 1010

Text #16

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.2274. Min Act: -0.0000

Data Index: 1141565 (The Pile)

Max Activating Token Index: 785

Text #17

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.2659. Min Act: -0.0000

Data Index: 80658 (The Pile)

Max Activating Token Index: 933

Text #18

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.2749. Min Act: -0.0000

Data Index: 1733024 (The Pile)

Max Activating Token Index: 828

Text #19

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.2280. Min Act: -0.0000

Data Index: 786477 (The Pile)

Max Activating Token Index: 442