Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 3046 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 1.1942. Min Range: -1.1942

Max Act: 1.1942. Min Act: -0.0000

Data Index: 1639014 (The Pile)

Max Activating Token Index: 623

Text #1

Max Range: 1.1942. Min Range: -1.1942

Max Act: 1.1555. Min Act: -0.0000

Data Index: 912576 (The Pile)

Max Activating Token Index: 466

Text #2

Max Range: 1.1942. Min Range: -1.1942

Max Act: 1.0552. Min Act: -0.0000

Data Index: 1418102 (The Pile)

Max Activating Token Index: 981

Text #3

Max Range: 1.1942. Min Range: -1.1942

Max Act: 1.0181. Min Act: -0.0000

Data Index: 196071 (The Pile)

Max Activating Token Index: 103

Text #4

Max Range: 1.1942. Min Range: -1.1942

Max Act: 0.9928. Min Act: -0.0000

Data Index: 1465463 (The Pile)

Max Activating Token Index: 643

Text #5

Max Range: 1.1942. Min Range: -1.1942

Max Act: 0.9812. Min Act: -0.0000

Data Index: 875450 (The Pile)

Max Activating Token Index: 556

Text #6

Max Range: 1.1942. Min Range: -1.1942

Max Act: 0.8349. Min Act: -0.0000

Data Index: 1200743 (The Pile)

Max Activating Token Index: 948

Text #7

Max Range: 1.1942. Min Range: -1.1942

Max Act: 0.9303. Min Act: 0.0000

Data Index: 209398 (The Pile)

Max Activating Token Index: 497

Text #8

Max Range: 1.1942. Min Range: -1.1942

Max Act: 0.8648. Min Act: -0.0000

Data Index: 1760267 (The Pile)

Max Activating Token Index: 175

Text #9

Max Range: 1.1942. Min Range: -1.1942

Max Act: 0.8120. Min Act: -0.0000

Data Index: 455527 (The Pile)

Max Activating Token Index: 972

Text #10

Max Range: 1.1942. Min Range: -1.1942

Max Act: 0.8263. Min Act: -0.0001

Data Index: 1624889 (The Pile)

Max Activating Token Index: 219

Text #11

Max Range: 1.1942. Min Range: -1.1942

Max Act: 0.8637. Min Act: -0.0001

Data Index: 1880639 (The Pile)

Max Activating Token Index: 842

Text #12

Max Range: 1.1942. Min Range: -1.1942

Max Act: 0.8145. Min Act: -0.0000

Data Index: 1461405 (The Pile)

Max Activating Token Index: 688

Text #13

Max Range: 1.1942. Min Range: -1.1942

Max Act: 0.8350. Min Act: 0.0001

Data Index: 757588 (The Pile)

Max Activating Token Index: 692

Text #14

Max Range: 1.1942. Min Range: -1.1942

Max Act: 0.8606. Min Act: -0.0000

Data Index: 893642 (The Pile)

Max Activating Token Index: 499

Text #15

Max Range: 1.1942. Min Range: -1.1942

Max Act: 0.8623. Min Act: -0.0000

Data Index: 1506848 (The Pile)

Max Activating Token Index: 374

Text #16

Max Range: 1.1942. Min Range: -1.1942

Max Act: 0.7996. Min Act: -0.0000

Data Index: 744453 (The Pile)

Max Activating Token Index: 293

Text #17

Max Range: 1.1942. Min Range: -1.1942

Max Act: 0.8400. Min Act: -0.0000

Data Index: 1156341 (The Pile)

Max Activating Token Index: 564

Text #18

Max Range: 1.1942. Min Range: -1.1942

Max Act: 0.8079. Min Act: -0.0000

Data Index: 737522 (The Pile)

Max Activating Token Index: 478

Text #19

Max Range: 1.1942. Min Range: -1.1942

Max Act: 0.8067. Min Act: -0.0000

Data Index: 99995 (The Pile)

Max Activating Token Index: 618