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

Dataset: The Pile

Neuron 2010 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7234. Min Range: -3.7234

Max Act: 3.7234. Min Act: -0.0000

Data Index: 1746492 (The Pile)

Max Activating Token Index: 26

Text #1

Max Range: 3.7234. Min Range: -3.7234

Max Act: 3.4735. Min Act: -0.0000

Data Index: 1192135 (The Pile)

Max Activating Token Index: 653

Text #2

Max Range: 3.7234. Min Range: -3.7234

Max Act: 3.4753. Min Act: -0.0000

Data Index: 1792488 (The Pile)

Max Activating Token Index: 939

Text #3

Max Range: 3.7234. Min Range: -3.7234

Max Act: 3.5658. Min Act: -0.0000

Data Index: 1427528 (The Pile)

Max Activating Token Index: 983

Text #4

Max Range: 3.7234. Min Range: -3.7234

Max Act: 3.4110. Min Act: -0.0000

Data Index: 587452 (The Pile)

Max Activating Token Index: 892

Text #5

Max Range: 3.7234. Min Range: -3.7234

Max Act: 3.4200. Min Act: -0.0000

Data Index: 824826 (The Pile)

Max Activating Token Index: 795

Text #6

Max Range: 3.7234. Min Range: -3.7234

Max Act: 3.0467. Min Act: -0.0000

Data Index: 1928209 (The Pile)

Max Activating Token Index: 579

Text #7

Max Range: 3.7234. Min Range: -3.7234

Max Act: 3.3389. Min Act: -0.0000

Data Index: 141940 (The Pile)

Max Activating Token Index: 392

Text #8

Max Range: 3.7234. Min Range: -3.7234

Max Act: 2.9020. Min Act: -0.0000

Data Index: 1830997 (The Pile)

Max Activating Token Index: 869

Text #9

Max Range: 3.7234. Min Range: -3.7234

Max Act: 3.1976. Min Act: -0.0000

Data Index: 1091504 (The Pile)

Max Activating Token Index: 636

Text #10

Max Range: 3.7234. Min Range: -3.7234

Max Act: 3.1427. Min Act: -0.0000

Data Index: 1328721 (The Pile)

Max Activating Token Index: 166

Text #11

Max Range: 3.7234. Min Range: -3.7234

Max Act: 3.1369. Min Act: -0.0000

Data Index: 1817647 (The Pile)

Max Activating Token Index: 347

Text #12

Max Range: 3.7234. Min Range: -3.7234

Max Act: 3.1004. Min Act: -0.0000

Data Index: 663440 (The Pile)

Max Activating Token Index: 908

Text #13

Max Range: 3.7234. Min Range: -3.7234

Max Act: 3.0970. Min Act: -0.0000

Data Index: 695074 (The Pile)

Max Activating Token Index: 364

Text #14

Max Range: 3.7234. Min Range: -3.7234

Max Act: 2.9243. Min Act: -0.0000

Data Index: 690385 (The Pile)

Max Activating Token Index: 962

Text #15

Max Range: 3.7234. Min Range: -3.7234

Max Act: 3.0723. Min Act: -0.0000

Data Index: 532850 (The Pile)

Max Activating Token Index: 849

Text #16

Max Range: 3.7234. Min Range: -3.7234

Max Act: 2.9126. Min Act: -0.0000

Data Index: 120814 (The Pile)

Max Activating Token Index: 695

Text #17

Max Range: 3.7234. Min Range: -3.7234

Max Act: 3.0574. Min Act: -0.0000

Data Index: 311033 (The Pile)

Max Activating Token Index: 359

Text #18

Max Range: 3.7234. Min Range: -3.7234

Max Act: 3.0611. Min Act: -0.0000

Data Index: 927875 (The Pile)

Max Activating Token Index: 856

Text #19

Max Range: 3.7234. Min Range: -3.7234

Max Act: 2.9059. Min Act: -0.0000

Data Index: 464197 (The Pile)

Max Activating Token Index: 325