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

Dataset: The Pile

Neuron 3002 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.4404. Min Range: -1.4404

Max Act: 1.4404. Min Act: -0.0000

Data Index: 344489 (The Pile)

Max Activating Token Index: 153

Text #1

Max Range: 1.4404. Min Range: -1.4404

Max Act: 1.4283. Min Act: -0.0000

Data Index: 562446 (The Pile)

Max Activating Token Index: 815

Text #2

Max Range: 1.4404. Min Range: -1.4404

Max Act: 1.3681. Min Act: -0.0000

Data Index: 256965 (The Pile)

Max Activating Token Index: 359

Text #3

Max Range: 1.4404. Min Range: -1.4404

Max Act: 1.4170. Min Act: -0.0000

Data Index: 651551 (The Pile)

Max Activating Token Index: 532

Text #4

Max Range: 1.4404. Min Range: -1.4404

Max Act: 1.3015. Min Act: -0.0000

Data Index: 1272117 (The Pile)

Max Activating Token Index: 780

Text #5

Max Range: 1.4404. Min Range: -1.4404

Max Act: 1.3311. Min Act: 0.0000

Data Index: 369997 (The Pile)

Max Activating Token Index: 777

Text #6

Max Range: 1.4404. Min Range: -1.4404

Max Act: 1.2393. Min Act: -0.0000

Data Index: 766462 (The Pile)

Max Activating Token Index: 687

Text #7

Max Range: 1.4404. Min Range: -1.4404

Max Act: 1.1677. Min Act: -0.0000

Data Index: 1223740 (The Pile)

Max Activating Token Index: 548

Text #8

Max Range: 1.4404. Min Range: -1.4404

Max Act: 1.1911. Min Act: -0.0000

Data Index: 656389 (The Pile)

Max Activating Token Index: 549

Text #9

Max Range: 1.4404. Min Range: -1.4404

Max Act: 1.2175. Min Act: -0.0000

Data Index: 1858942 (The Pile)

Max Activating Token Index: 496

Text #10

Max Range: 1.4404. Min Range: -1.4404

Max Act: 1.1724. Min Act: -0.0000

Data Index: 1005987 (The Pile)

Max Activating Token Index: 903

Text #11

Max Range: 1.4404. Min Range: -1.4404

Max Act: 1.1450. Min Act: -0.0000

Data Index: 1426737 (The Pile)

Max Activating Token Index: 637

Text #12

Max Range: 1.4404. Min Range: -1.4404

Max Act: 1.1763. Min Act: -0.0000

Data Index: 1621284 (The Pile)

Max Activating Token Index: 309

Text #13

Max Range: 1.4404. Min Range: -1.4404

Max Act: 1.2039. Min Act: -0.0000

Data Index: 1153928 (The Pile)

Max Activating Token Index: 544

Text #14

Max Range: 1.4404. Min Range: -1.4404

Max Act: 1.2025. Min Act: -0.0000

Data Index: 339102 (The Pile)

Max Activating Token Index: 924

Text #15

Max Range: 1.4404. Min Range: -1.4404

Max Act: 1.1391. Min Act: -0.0000

Data Index: 715414 (The Pile)

Max Activating Token Index: 711

Text #16

Max Range: 1.4404. Min Range: -1.4404

Max Act: 1.1384. Min Act: -0.0000

Data Index: 796516 (The Pile)

Max Activating Token Index: 189

Text #17

Max Range: 1.4404. Min Range: -1.4404

Max Act: 1.1385. Min Act: -0.0000

Data Index: 1721838 (The Pile)

Max Activating Token Index: 519

Text #18

Max Range: 1.4404. Min Range: -1.4404

Max Act: 1.1688. Min Act: -0.0000

Data Index: 1329436 (The Pile)

Max Activating Token Index: 384

Text #19

Max Range: 1.4404. Min Range: -1.4404

Max Act: 1.0978. Min Act: -0.0000

Data Index: 1463058 (The Pile)

Max Activating Token Index: 560