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

Dataset: The Pile

Neuron 2093 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9651. Min Range: -0.9651

Max Act: 0.9651. Min Act: -0.0000

Data Index: 393423 (The Pile)

Max Activating Token Index: 646

Text #1

Max Range: 0.9651. Min Range: -0.9651

Max Act: 0.9493. Min Act: -0.0000

Data Index: 1278849 (The Pile)

Max Activating Token Index: 52

Text #2

Max Range: 0.9651. Min Range: -0.9651

Max Act: 0.9309. Min Act: -0.0000

Data Index: 11686 (The Pile)

Max Activating Token Index: 105

Text #3

Max Range: 0.9651. Min Range: -0.9651

Max Act: 0.9066. Min Act: -0.0000

Data Index: 270562 (The Pile)

Max Activating Token Index: 103

Text #4

Max Range: 0.9651. Min Range: -0.9651

Max Act: 0.8621. Min Act: -0.0000

Data Index: 1728961 (The Pile)

Max Activating Token Index: 423

Text #5

Max Range: 0.9651. Min Range: -0.9651

Max Act: 0.7601. Min Act: -0.0000

Data Index: 1344511 (The Pile)

Max Activating Token Index: 778

Text #6

Max Range: 0.9651. Min Range: -0.9651

Max Act: 0.7530. Min Act: -0.0000

Data Index: 137589 (The Pile)

Max Activating Token Index: 854

Text #7

Max Range: 0.9651. Min Range: -0.9651

Max Act: 0.8048. Min Act: -0.0000

Data Index: 1433422 (The Pile)

Max Activating Token Index: 501

Text #8

Max Range: 0.9651. Min Range: -0.9651

Max Act: 0.7907. Min Act: -0.0000

Data Index: 1207674 (The Pile)

Max Activating Token Index: 496

Text #9

Max Range: 0.9651. Min Range: -0.9651

Max Act: 0.7268. Min Act: -0.0000

Data Index: 1562930 (The Pile)

Max Activating Token Index: 627

Text #10

Max Range: 0.9651. Min Range: -0.9651

Max Act: 0.7444. Min Act: -0.0000

Data Index: 1217709 (The Pile)

Max Activating Token Index: 873

Text #11

Max Range: 0.9651. Min Range: -0.9651

Max Act: 0.6965. Min Act: -0.0000

Data Index: 348765 (The Pile)

Max Activating Token Index: 900

Text #12

Max Range: 0.9651. Min Range: -0.9651

Max Act: 0.7011. Min Act: -0.0000

Data Index: 700866 (The Pile)

Max Activating Token Index: 113

Text #13

Max Range: 0.9651. Min Range: -0.9651

Max Act: 0.7416. Min Act: -0.0000

Data Index: 1921536 (The Pile)

Max Activating Token Index: 766

Text #14

Max Range: 0.9651. Min Range: -0.9651

Max Act: 0.6967. Min Act: -0.0000

Data Index: 1681337 (The Pile)

Max Activating Token Index: 317

Text #15

Max Range: 0.9651. Min Range: -0.9651

Max Act: 0.7280. Min Act: -0.0000

Data Index: 497426 (The Pile)

Max Activating Token Index: 313

Text #16

Max Range: 0.9651. Min Range: -0.9651

Max Act: 0.6446. Min Act: -0.0000

Data Index: 236586 (The Pile)

Max Activating Token Index: 552

Text #17

Max Range: 0.9651. Min Range: -0.9651

Max Act: 0.7208. Min Act: -0.0000

Data Index: 1483785 (The Pile)

Max Activating Token Index: 77

Text #18

Max Range: 0.9651. Min Range: -0.9651

Max Act: 0.7600. Min Act: -0.0000

Data Index: 1140873 (The Pile)

Max Activating Token Index: 74

Text #19

Max Range: 0.9651. Min Range: -0.9651

Max Act: 0.7513. Min Act: -0.0000

Data Index: 641183 (The Pile)

Max Activating Token Index: 975