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

Dataset: The Pile

Neuron 4840 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: 1.4289. Min Range: -1.4289

Max Act: 1.3892. Min Act: -0.0000

Data Index: 357485 (The Pile)

Max Activating Token Index: 339

Text #1

Max Range: 1.4289. Min Range: -1.4289

Max Act: 1.4289. Min Act: -0.0000

Data Index: 1538715 (The Pile)

Max Activating Token Index: 96

Text #2

Max Range: 1.4289. Min Range: -1.4289

Max Act: 1.2214. Min Act: -0.0000

Data Index: 91633 (The Pile)

Max Activating Token Index: 983

Text #3

Max Range: 1.4289. Min Range: -1.4289

Max Act: 1.1195. Min Act: -0.0000

Data Index: 1816093 (The Pile)

Max Activating Token Index: 420

Text #4

Max Range: 1.4289. Min Range: -1.4289

Max Act: 1.1467. Min Act: -0.0000

Data Index: 1336683 (The Pile)

Max Activating Token Index: 795

Text #5

Max Range: 1.4289. Min Range: -1.4289

Max Act: 0.9729. Min Act: -0.0000

Data Index: 1108655 (The Pile)

Max Activating Token Index: 857

Text #6

Max Range: 1.4289. Min Range: -1.4289

Max Act: 1.0625. Min Act: -0.0000

Data Index: 1800453 (The Pile)

Max Activating Token Index: 467

Text #7

Max Range: 1.4289. Min Range: -1.4289

Max Act: 0.8948. Min Act: -0.0000

Data Index: 693390 (The Pile)

Max Activating Token Index: 737

Text #8

Max Range: 1.4289. Min Range: -1.4289

Max Act: 0.9473. Min Act: -0.0000

Data Index: 912357 (The Pile)

Max Activating Token Index: 343

Text #9

Max Range: 1.4289. Min Range: -1.4289

Max Act: 1.0384. Min Act: -0.0000

Data Index: 1324499 (The Pile)

Max Activating Token Index: 843

Text #10

Max Range: 1.4289. Min Range: -1.4289

Max Act: 0.9734. Min Act: -0.0000

Data Index: 1639796 (The Pile)

Max Activating Token Index: 243

Text #11

Max Range: 1.4289. Min Range: -1.4289

Max Act: 0.8811. Min Act: -0.0000

Data Index: 1102378 (The Pile)

Max Activating Token Index: 935

Text #12

Max Range: 1.4289. Min Range: -1.4289

Max Act: 0.8532. Min Act: -0.0000

Data Index: 996346 (The Pile)

Max Activating Token Index: 365

Text #13

Max Range: 1.4289. Min Range: -1.4289

Max Act: 0.8739. Min Act: -0.0000

Data Index: 54572 (The Pile)

Max Activating Token Index: 365

Text #14

Max Range: 1.4289. Min Range: -1.4289

Max Act: 0.8488. Min Act: -0.0000

Data Index: 715155 (The Pile)

Max Activating Token Index: 253

Text #15

Max Range: 1.4289. Min Range: -1.4289

Max Act: 0.8925. Min Act: -0.0000

Data Index: 1796634 (The Pile)

Max Activating Token Index: 236

Text #16

Max Range: 1.4289. Min Range: -1.4289

Max Act: 0.8510. Min Act: -0.0000

Data Index: 1674286 (The Pile)

Max Activating Token Index: 383

Text #17

Max Range: 1.4289. Min Range: -1.4289

Max Act: 0.8445. Min Act: -0.0000

Data Index: 774038 (The Pile)

Max Activating Token Index: 994

Text #18

Max Range: 1.4289. Min Range: -1.4289

Max Act: 0.8352. Min Act: -0.0000

Data Index: 566906 (The Pile)

Max Activating Token Index: 145

Text #19

Max Range: 1.4289. Min Range: -1.4289

Max Act: 0.7562. Min Act: -0.0000

Data Index: 557164 (The Pile)

Max Activating Token Index: 26