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

Dataset: The Pile

Neuron 3796 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: 1.1393. Min Range: -1.1393

Max Act: 1.1393. Min Act: -0.0000

Data Index: 972205 (The Pile)

Max Activating Token Index: 93

Text #1

Max Range: 1.1393. Min Range: -1.1393

Max Act: 0.9409. Min Act: -0.0000

Data Index: 1823720 (The Pile)

Max Activating Token Index: 385

Text #2

Max Range: 1.1393. Min Range: -1.1393

Max Act: 0.8397. Min Act: -0.0000

Data Index: 999649 (The Pile)

Max Activating Token Index: 962

Text #3

Max Range: 1.1393. Min Range: -1.1393

Max Act: 0.8502. Min Act: -0.0000

Data Index: 1227865 (The Pile)

Max Activating Token Index: 701

Text #4

Max Range: 1.1393. Min Range: -1.1393

Max Act: 0.7347. Min Act: -0.0000

Data Index: 599695 (The Pile)

Max Activating Token Index: 866

Text #5

Max Range: 1.1393. Min Range: -1.1393

Max Act: 0.6981. Min Act: -0.0000

Data Index: 709175 (The Pile)

Max Activating Token Index: 436

Text #6

Max Range: 1.1393. Min Range: -1.1393

Max Act: 0.6370. Min Act: -0.0000

Data Index: 1688218 (The Pile)

Max Activating Token Index: 884

Text #7

Max Range: 1.1393. Min Range: -1.1393

Max Act: 0.6287. Min Act: -0.0000

Data Index: 788487 (The Pile)

Max Activating Token Index: 401

Text #8

Max Range: 1.1393. Min Range: -1.1393

Max Act: 0.5913. Min Act: -0.0000

Data Index: 1278709 (The Pile)

Max Activating Token Index: 990

Text #9

Max Range: 1.1393. Min Range: -1.1393

Max Act: 0.5446. Min Act: -0.0000

Data Index: 1825759 (The Pile)

Max Activating Token Index: 507

Text #10

Max Range: 1.1393. Min Range: -1.1393

Max Act: 0.5409. Min Act: -0.0000

Data Index: 599964 (The Pile)

Max Activating Token Index: 944

Text #11

Max Range: 1.1393. Min Range: -1.1393

Max Act: 0.5924. Min Act: -0.0000

Data Index: 1862628 (The Pile)

Max Activating Token Index: 93

Text #12

Max Range: 1.1393. Min Range: -1.1393

Max Act: 0.6182. Min Act: -0.0000

Data Index: 996013 (The Pile)

Max Activating Token Index: 884

Text #13

Max Range: 1.1393. Min Range: -1.1393

Max Act: 0.5439. Min Act: -0.0000

Data Index: 1032809 (The Pile)

Max Activating Token Index: 510

Text #14

Max Range: 1.1393. Min Range: -1.1393

Max Act: 0.5615. Min Act: -0.0000

Data Index: 185046 (The Pile)

Max Activating Token Index: 138

Text #15

Max Range: 1.1393. Min Range: -1.1393

Max Act: 0.5794. Min Act: -0.0000

Data Index: 1481331 (The Pile)

Max Activating Token Index: 677

Text #16

Max Range: 1.1393. Min Range: -1.1393

Max Act: 0.5458. Min Act: -0.0000

Data Index: 1532953 (The Pile)

Max Activating Token Index: 480

Text #17

Max Range: 1.1393. Min Range: -1.1393

Max Act: 0.5582. Min Act: -0.0000

Data Index: 1021102 (The Pile)

Max Activating Token Index: 40

Text #18

Max Range: 1.1393. Min Range: -1.1393

Max Act: 0.4597. Min Act: -0.0000

Data Index: 154771 (The Pile)

Max Activating Token Index: 611

Text #19

Max Range: 1.1393. Min Range: -1.1393

Max Act: 0.5416. Min Act: -0.0000

Data Index: 594643 (The Pile)

Max Activating Token Index: 500