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

Dataset: The Pile

Neuron 1513 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: 1.3963. Min Range: -1.3963

Max Act: 1.3963. Min Act: -0.0000

Data Index: 1496382 (The Pile)

Max Activating Token Index: 695

Text #1

Max Range: 1.3963. Min Range: -1.3963

Max Act: 1.3946. Min Act: -0.0000

Data Index: 1015379 (The Pile)

Max Activating Token Index: 749

Text #2

Max Range: 1.3963. Min Range: -1.3963

Max Act: 1.1256. Min Act: -0.0000

Data Index: 1869941 (The Pile)

Max Activating Token Index: 754

Text #3

Max Range: 1.3963. Min Range: -1.3963

Max Act: 1.1112. Min Act: -0.0000

Data Index: 1218480 (The Pile)

Max Activating Token Index: 520

Text #4

Max Range: 1.3963. Min Range: -1.3963

Max Act: 1.0351. Min Act: -0.0000

Data Index: 901462 (The Pile)

Max Activating Token Index: 606

Text #5

Max Range: 1.3963. Min Range: -1.3963

Max Act: 1.0370. Min Act: -0.0000

Data Index: 1354632 (The Pile)

Max Activating Token Index: 511

Text #6

Max Range: 1.3963. Min Range: -1.3963

Max Act: 0.9481. Min Act: -0.0000

Data Index: 1580561 (The Pile)

Max Activating Token Index: 285

Text #7

Max Range: 1.3963. Min Range: -1.3963

Max Act: 1.0867. Min Act: -0.0000

Data Index: 1855749 (The Pile)

Max Activating Token Index: 397

Text #8

Max Range: 1.3963. Min Range: -1.3963

Max Act: 0.9028. Min Act: -0.0000

Data Index: 1087127 (The Pile)

Max Activating Token Index: 780

Text #9

Max Range: 1.3963. Min Range: -1.3963

Max Act: 0.8284. Min Act: -0.0000

Data Index: 1231622 (The Pile)

Max Activating Token Index: 488

Text #10

Max Range: 1.3963. Min Range: -1.3963

Max Act: 0.8584. Min Act: -0.0000

Data Index: 1554513 (The Pile)

Max Activating Token Index: 641

Text #11

Max Range: 1.3963. Min Range: -1.3963

Max Act: 0.8549. Min Act: -0.0000

Data Index: 1236773 (The Pile)

Max Activating Token Index: 122

Text #12

Max Range: 1.3963. Min Range: -1.3963

Max Act: 0.8452. Min Act: -0.0000

Data Index: 1465713 (The Pile)

Max Activating Token Index: 739

Text #13

Max Range: 1.3963. Min Range: -1.3963

Max Act: 0.8885. Min Act: -0.0000

Data Index: 136344 (The Pile)

Max Activating Token Index: 659

Text #14

Max Range: 1.3963. Min Range: -1.3963

Max Act: 0.8315. Min Act: -0.0000

Data Index: 437939 (The Pile)

Max Activating Token Index: 943

Text #15

Max Range: 1.3963. Min Range: -1.3963

Max Act: 0.9012. Min Act: -0.0000

Data Index: 1383897 (The Pile)

Max Activating Token Index: 415

Text #16

Max Range: 1.3963. Min Range: -1.3963

Max Act: 0.8340. Min Act: -0.0000

Data Index: 420456 (The Pile)

Max Activating Token Index: 853

Text #17

Max Range: 1.3963. Min Range: -1.3963

Max Act: 0.8446. Min Act: -0.0000

Data Index: 1397911 (The Pile)

Max Activating Token Index: 664

Text #18

Max Range: 1.3963. Min Range: -1.3963

Max Act: 0.8795. Min Act: -0.0000

Data Index: 431610 (The Pile)

Max Activating Token Index: 923

Text #19

Max Range: 1.3963. Min Range: -1.3963

Max Act: 0.8070. Min Act: -0.0000

Data Index: 461106 (The Pile)

Max Activating Token Index: 954