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

Dataset: The Pile

Neuron 2119 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: 1.8026. Min Range: -1.8026

Max Act: 1.7105. Min Act: -0.0000

Data Index: 1917035 (The Pile)

Max Activating Token Index: 28

Text #1

Max Range: 1.8026. Min Range: -1.8026

Max Act: 1.8026. Min Act: -0.0000

Data Index: 1361558 (The Pile)

Max Activating Token Index: 607

Text #2

Max Range: 1.8026. Min Range: -1.8026

Max Act: 1.6976. Min Act: -0.0000

Data Index: 978203 (The Pile)

Max Activating Token Index: 702

Text #3

Max Range: 1.8026. Min Range: -1.8026

Max Act: 1.6853. Min Act: -0.0000

Data Index: 1942568 (The Pile)

Max Activating Token Index: 500

Text #4

Max Range: 1.8026. Min Range: -1.8026

Max Act: 1.5725. Min Act: -0.0000

Data Index: 1431455 (The Pile)

Max Activating Token Index: 716

Text #5

Max Range: 1.8026. Min Range: -1.8026

Max Act: 1.7328. Min Act: -0.0000

Data Index: 1981268 (The Pile)

Max Activating Token Index: 947

Text #6

Max Range: 1.8026. Min Range: -1.8026

Max Act: 1.6271. Min Act: -0.0000

Data Index: 1663744 (The Pile)

Max Activating Token Index: 937

Text #7

Max Range: 1.8026. Min Range: -1.8026

Max Act: 1.4816. Min Act: -0.0000

Data Index: 1918299 (The Pile)

Max Activating Token Index: 943

Text #8

Max Range: 1.8026. Min Range: -1.8026

Max Act: 1.3919. Min Act: -0.0000

Data Index: 661568 (The Pile)

Max Activating Token Index: 825

Text #9

Max Range: 1.8026. Min Range: -1.8026

Max Act: 1.5239. Min Act: -0.0000

Data Index: 779281 (The Pile)

Max Activating Token Index: 549

Text #10

Max Range: 1.8026. Min Range: -1.8026

Max Act: 1.5306. Min Act: -0.0000

Data Index: 1543988 (The Pile)

Max Activating Token Index: 497

Text #11

Max Range: 1.8026. Min Range: -1.8026

Max Act: 1.5227. Min Act: -0.0000

Data Index: 1520065 (The Pile)

Max Activating Token Index: 414

Text #12

Max Range: 1.8026. Min Range: -1.8026

Max Act: 1.4581. Min Act: -0.0000

Data Index: 1625986 (The Pile)

Max Activating Token Index: 664

Text #13

Max Range: 1.8026. Min Range: -1.8026

Max Act: 1.4468. Min Act: -0.0000

Data Index: 1627811 (The Pile)

Max Activating Token Index: 64

Text #14

Max Range: 1.8026. Min Range: -1.8026

Max Act: 1.4601. Min Act: -0.0000

Data Index: 468089 (The Pile)

Max Activating Token Index: 690

Text #15

Max Range: 1.8026. Min Range: -1.8026

Max Act: 1.4626. Min Act: -0.0000

Data Index: 1970012 (The Pile)

Max Activating Token Index: 722

Text #16

Max Range: 1.8026. Min Range: -1.8026

Max Act: 1.4436. Min Act: -0.0000

Data Index: 737077 (The Pile)

Max Activating Token Index: 478

Text #17

Max Range: 1.8026. Min Range: -1.8026

Max Act: 1.4739. Min Act: -0.0000

Data Index: 886584 (The Pile)

Max Activating Token Index: 439

Text #18

Max Range: 1.8026. Min Range: -1.8026

Max Act: 1.4679. Min Act: -0.0000

Data Index: 978935 (The Pile)

Max Activating Token Index: 371

Text #19

Max Range: 1.8026. Min Range: -1.8026

Max Act: 1.3822. Min Act: -0.0000

Data Index: 1383928 (The Pile)

Max Activating Token Index: 320