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

Dataset: The Pile

Neuron 1830 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: 0.8398. Min Range: -0.8398

Max Act: 0.8398. Min Act: -0.0000

Data Index: 212326 (The Pile)

Max Activating Token Index: 405

Text #1

Max Range: 0.8398. Min Range: -0.8398

Max Act: 0.4797. Min Act: -0.0000

Data Index: 1885022 (The Pile)

Max Activating Token Index: 742

Text #2

Max Range: 0.8398. Min Range: -0.8398

Max Act: 0.6890. Min Act: -0.0000

Data Index: 1456429 (The Pile)

Max Activating Token Index: 76

Text #3

Max Range: 0.8398. Min Range: -0.8398

Max Act: 0.6737. Min Act: -0.0000

Data Index: 465589 (The Pile)

Max Activating Token Index: 4

Text #4

Max Range: 0.8398. Min Range: -0.8398

Max Act: 0.5658. Min Act: -0.0000

Data Index: 1087160 (The Pile)

Max Activating Token Index: 364

Text #5

Max Range: 0.8398. Min Range: -0.8398

Max Act: 0.6168. Min Act: -0.0000

Data Index: 1513519 (The Pile)

Max Activating Token Index: 438

Text #6

Max Range: 0.8398. Min Range: -0.8398

Max Act: 0.6099. Min Act: -0.0000

Data Index: 100923 (The Pile)

Max Activating Token Index: 964

Text #7

Max Range: 0.8398. Min Range: -0.8398

Max Act: 0.4978. Min Act: -0.0000

Data Index: 1994855 (The Pile)

Max Activating Token Index: 946

Text #8

Max Range: 0.8398. Min Range: -0.8398

Max Act: 0.6018. Min Act: -0.0000

Data Index: 775019 (The Pile)

Max Activating Token Index: 355

Text #9

Max Range: 0.8398. Min Range: -0.8398

Max Act: 0.4568. Min Act: -0.0000

Data Index: 293831 (The Pile)

Max Activating Token Index: 765

Text #10

Max Range: 0.8398. Min Range: -0.8398

Max Act: 0.5727. Min Act: -0.0000

Data Index: 1719103 (The Pile)

Max Activating Token Index: 445

Text #11

Max Range: 0.8398. Min Range: -0.8398

Max Act: 0.5313. Min Act: -0.0000

Data Index: 604005 (The Pile)

Max Activating Token Index: 993

Text #12

Max Range: 0.8398. Min Range: -0.8398

Max Act: 0.5554. Min Act: -0.0000

Data Index: 895906 (The Pile)

Max Activating Token Index: 719

Text #13

Max Range: 0.8398. Min Range: -0.8398

Max Act: 0.4853. Min Act: -0.0000

Data Index: 1839469 (The Pile)

Max Activating Token Index: 457

Text #14

Max Range: 0.8398. Min Range: -0.8398

Max Act: 0.4682. Min Act: -0.0000

Data Index: 1048333 (The Pile)

Max Activating Token Index: 920

Text #15

Max Range: 0.8398. Min Range: -0.8398

Max Act: 0.5318. Min Act: -0.0000

Data Index: 902248 (The Pile)

Max Activating Token Index: 604

Text #16

Max Range: 0.8398. Min Range: -0.8398

Max Act: 0.4931. Min Act: -0.0000

Data Index: 700515 (The Pile)

Max Activating Token Index: 974

Text #17

Max Range: 0.8398. Min Range: -0.8398

Max Act: 0.5499. Min Act: -0.0000

Data Index: 748977 (The Pile)

Max Activating Token Index: 476

Text #18

Max Range: 0.8398. Min Range: -0.8398

Max Act: 0.5015. Min Act: -0.0000

Data Index: 1363880 (The Pile)

Max Activating Token Index: 698

Text #19

Max Range: 0.8398. Min Range: -0.8398

Max Act: 0.4801. Min Act: -0.0000

Data Index: 1043784 (The Pile)

Max Activating Token Index: 748