Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1371 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 10.1587. Min Range: -10.1587

Max Act: 10.1587. Min Act: -0.0000

Data Index: 410992 (C4 (Web Text))

Max Activating Token Index: 54

Text #1

Max Range: 10.1587. Min Range: -10.1587

Max Act: 9.9248. Min Act: -0.0000

Data Index: 1322030 (C4 (Web Text))

Max Activating Token Index: 147

Text #2

Max Range: 10.1587. Min Range: -10.1587

Max Act: 9.4784. Min Act: -0.0000

Data Index: 553663 (C4 (Web Text))

Max Activating Token Index: 242

Text #3

Max Range: 10.1587. Min Range: -10.1587

Max Act: 9.4973. Min Act: -0.0000

Data Index: 707324 (C4 (Web Text))

Max Activating Token Index: 429

Text #4

Max Range: 10.1587. Min Range: -10.1587

Max Act: 9.5580. Min Act: -0.0000

Data Index: 840370 (C4 (Web Text))

Max Activating Token Index: 17

Text #5

Max Range: 10.1587. Min Range: -10.1587

Max Act: 9.4360. Min Act: -0.0000

Data Index: 977165 (C4 (Web Text))

Max Activating Token Index: 801

Text #6

Max Range: 10.1587. Min Range: -10.1587

Max Act: 8.9606. Min Act: -0.0000

Data Index: 892553 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 10.1587. Min Range: -10.1587

Max Act: 9.1090. Min Act: -0.0000

Data Index: 761812 (C4 (Web Text))

Max Activating Token Index: 7

Text #8

Max Range: 10.1587. Min Range: -10.1587

Max Act: 8.9484. Min Act: -0.0000

Data Index: 298690 (C4 (Web Text))

Max Activating Token Index: 434

Text #9

Max Range: 10.1587. Min Range: -10.1587

Max Act: 8.7684. Min Act: -0.0000

Data Index: 639491 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 10.1587. Min Range: -10.1587

Max Act: 8.8862. Min Act: -0.0000

Data Index: 59196 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 10.1587. Min Range: -10.1587

Max Act: 8.9894. Min Act: -0.0000

Data Index: 306769 (C4 (Web Text))

Max Activating Token Index: 25

Text #12

Max Range: 10.1587. Min Range: -10.1587

Max Act: 8.7587. Min Act: -0.0000

Data Index: 337481 (C4 (Web Text))

Max Activating Token Index: 12

Text #13

Max Range: 10.1587. Min Range: -10.1587

Max Act: 8.4299. Min Act: -0.0000

Data Index: 1332804 (C4 (Web Text))

Max Activating Token Index: 810

Text #14

Max Range: 10.1587. Min Range: -10.1587

Max Act: 8.4408. Min Act: -0.0000

Data Index: 631073 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 10.1587. Min Range: -10.1587

Max Act: 8.4887. Min Act: -0.0000

Data Index: 1271749 (C4 (Web Text))

Max Activating Token Index: 887

Text #16

Max Range: 10.1587. Min Range: -10.1587

Max Act: 8.4617. Min Act: -0.0000

Data Index: 357200 (C4 (Web Text))

Max Activating Token Index: 91

Text #17

Max Range: 10.1587. Min Range: -10.1587

Max Act: 8.6186. Min Act: -0.0000

Data Index: 80886 (C4 (Web Text))

Max Activating Token Index: 19

Text #18

Max Range: 10.1587. Min Range: -10.1587

Max Act: 8.3900. Min Act: -0.0000

Data Index: 468445 (C4 (Web Text))

Max Activating Token Index: 14

Text #19

Max Range: 10.1587. Min Range: -10.1587

Max Act: 8.2164. Min Act: -0.0000

Data Index: 227070 (C4 (Web Text))

Max Activating Token Index: 10