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

Dataset: The Pile

Neuron 480 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: 1.6040. Min Range: -1.6040

Max Act: 1.5458. Min Act: -0.0000

Data Index: 1360445 (The Pile)

Max Activating Token Index: 277

Text #1

Max Range: 1.6040. Min Range: -1.6040

Max Act: 1.5982. Min Act: -0.0000

Data Index: 1034115 (The Pile)

Max Activating Token Index: 269

Text #2

Max Range: 1.6040. Min Range: -1.6040

Max Act: 1.6040. Min Act: -0.0000

Data Index: 766214 (The Pile)

Max Activating Token Index: 427

Text #3

Max Range: 1.6040. Min Range: -1.6040

Max Act: 1.4075. Min Act: -0.0000

Data Index: 598639 (The Pile)

Max Activating Token Index: 539

Text #4

Max Range: 1.6040. Min Range: -1.6040

Max Act: 1.5000. Min Act: -0.0000

Data Index: 387362 (The Pile)

Max Activating Token Index: 465

Text #5

Max Range: 1.6040. Min Range: -1.6040

Max Act: 1.4448. Min Act: -0.0000

Data Index: 1078144 (The Pile)

Max Activating Token Index: 395

Text #6

Max Range: 1.6040. Min Range: -1.6040

Max Act: 1.3719. Min Act: -0.0000

Data Index: 211314 (The Pile)

Max Activating Token Index: 334

Text #7

Max Range: 1.6040. Min Range: -1.6040

Max Act: 1.3015. Min Act: -0.0000

Data Index: 1273786 (The Pile)

Max Activating Token Index: 362

Text #8

Max Range: 1.6040. Min Range: -1.6040

Max Act: 1.2299. Min Act: -0.0000

Data Index: 893860 (The Pile)

Max Activating Token Index: 575

Text #9

Max Range: 1.6040. Min Range: -1.6040

Max Act: 1.2085. Min Act: -0.0000

Data Index: 1271566 (The Pile)

Max Activating Token Index: 57

Text #10

Max Range: 1.6040. Min Range: -1.6040

Max Act: 1.1845. Min Act: -0.0000

Data Index: 1045379 (The Pile)

Max Activating Token Index: 579

Text #11

Max Range: 1.6040. Min Range: -1.6040

Max Act: 1.2026. Min Act: -0.0000

Data Index: 1077230 (The Pile)

Max Activating Token Index: 543

Text #12

Max Range: 1.6040. Min Range: -1.6040

Max Act: 1.1411. Min Act: -0.0000

Data Index: 1514823 (The Pile)

Max Activating Token Index: 787

Text #13

Max Range: 1.6040. Min Range: -1.6040

Max Act: 1.1297. Min Act: -0.0000

Data Index: 284836 (The Pile)

Max Activating Token Index: 34

Text #14

Max Range: 1.6040. Min Range: -1.6040

Max Act: 1.1109. Min Act: -0.0000

Data Index: 1796812 (The Pile)

Max Activating Token Index: 912

Text #15

Max Range: 1.6040. Min Range: -1.6040

Max Act: 1.0739. Min Act: -0.0000

Data Index: 956362 (The Pile)

Max Activating Token Index: 772

Text #16

Max Range: 1.6040. Min Range: -1.6040

Max Act: 1.0910. Min Act: -0.0000

Data Index: 1141122 (The Pile)

Max Activating Token Index: 900

Text #17

Max Range: 1.6040. Min Range: -1.6040

Max Act: 0.8542. Min Act: -0.0000

Data Index: 924902 (The Pile)

Max Activating Token Index: 876

Text #18

Max Range: 1.6040. Min Range: -1.6040

Max Act: 0.8268. Min Act: -0.0000

Data Index: 551486 (The Pile)

Max Activating Token Index: 37

Text #19

Max Range: 1.6040. Min Range: -1.6040

Max Act: 0.8962. Min Act: -0.0000

Data Index: 497476 (The Pile)

Max Activating Token Index: 914