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

Dataset: The Pile

Neuron 3504 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: 1.2664. Min Range: -1.2664

Max Act: 1.2664. Min Act: -0.0000

Data Index: 1833586 (The Pile)

Max Activating Token Index: 399

Text #1

Max Range: 1.2664. Min Range: -1.2664

Max Act: 1.1446. Min Act: -0.0000

Data Index: 1834128 (The Pile)

Max Activating Token Index: 970

Text #2

Max Range: 1.2664. Min Range: -1.2664

Max Act: 1.0066. Min Act: -0.0000

Data Index: 17570 (The Pile)

Max Activating Token Index: 19

Text #3

Max Range: 1.2664. Min Range: -1.2664

Max Act: 0.9623. Min Act: -0.0000

Data Index: 1321006 (The Pile)

Max Activating Token Index: 667

Text #4

Max Range: 1.2664. Min Range: -1.2664

Max Act: 0.9086. Min Act: -0.0000

Data Index: 500457 (The Pile)

Max Activating Token Index: 460

Text #5

Max Range: 1.2664. Min Range: -1.2664

Max Act: 0.8920. Min Act: -0.0000

Data Index: 258099 (The Pile)

Max Activating Token Index: 356

Text #6

Max Range: 1.2664. Min Range: -1.2664

Max Act: 0.8640. Min Act: -0.0000

Data Index: 141662 (The Pile)

Max Activating Token Index: 633

Text #7

Max Range: 1.2664. Min Range: -1.2664

Max Act: 0.9219. Min Act: -0.0000

Data Index: 1741197 (The Pile)

Max Activating Token Index: 315

Text #8

Max Range: 1.2664. Min Range: -1.2664

Max Act: 0.8473. Min Act: -0.0000

Data Index: 1925235 (The Pile)

Max Activating Token Index: 707

Text #9

Max Range: 1.2664. Min Range: -1.2664

Max Act: 0.8601. Min Act: -0.0000

Data Index: 1503032 (The Pile)

Max Activating Token Index: 531

Text #10

Max Range: 1.2664. Min Range: -1.2664

Max Act: 0.8556. Min Act: -0.0000

Data Index: 1691086 (The Pile)

Max Activating Token Index: 51

Text #11

Max Range: 1.2664. Min Range: -1.2664

Max Act: 0.8344. Min Act: -0.0000

Data Index: 551214 (The Pile)

Max Activating Token Index: 699

Text #12

Max Range: 1.2664. Min Range: -1.2664

Max Act: 0.8504. Min Act: -0.0000

Data Index: 1449280 (The Pile)

Max Activating Token Index: 879

Text #13

Max Range: 1.2664. Min Range: -1.2664

Max Act: 0.8229. Min Act: -0.0000

Data Index: 402709 (The Pile)

Max Activating Token Index: 372

Text #14

Max Range: 1.2664. Min Range: -1.2664

Max Act: 0.8203. Min Act: -0.0000

Data Index: 662384 (The Pile)

Max Activating Token Index: 520

Text #15

Max Range: 1.2664. Min Range: -1.2664

Max Act: 0.7844. Min Act: -0.0000

Data Index: 615994 (The Pile)

Max Activating Token Index: 13

Text #16

Max Range: 1.2664. Min Range: -1.2664

Max Act: 0.8035. Min Act: -0.0000

Data Index: 1905509 (The Pile)

Max Activating Token Index: 909

Text #17

Max Range: 1.2664. Min Range: -1.2664

Max Act: 0.7738. Min Act: -0.0000

Data Index: 1639840 (The Pile)

Max Activating Token Index: 988

Text #18

Max Range: 1.2664. Min Range: -1.2664

Max Act: 0.7490. Min Act: -0.0000

Data Index: 551973 (The Pile)

Max Activating Token Index: 227

Text #19

Max Range: 1.2664. Min Range: -1.2664

Max Act: 0.7479. Min Act: -0.0000

Data Index: 43103 (The Pile)

Max Activating Token Index: 279