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

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

Neuron 2978 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6192. Min Range: -1.6192

Max Act: 1.6124. Min Act: -0.0002

Data Index: 559854 (C4 (Web Text))

Max Activating Token Index: 703

Text #1

Max Range: 1.6192. Min Range: -1.6192

Max Act: 1.6192. Min Act: -0.0002

Data Index: 1166710 (C4 (Web Text))

Max Activating Token Index: 216

Text #2

Max Range: 1.6192. Min Range: -1.6192

Max Act: 1.5516. Min Act: -0.0002

Data Index: 602451 (C4 (Web Text))

Max Activating Token Index: 694

Text #3

Max Range: 1.6192. Min Range: -1.6192

Max Act: 1.4676. Min Act: -0.0002

Data Index: 564890 (C4 (Web Text))

Max Activating Token Index: 514

Text #4

Max Range: 1.6192. Min Range: -1.6192

Max Act: 1.5441. Min Act: -0.0001

Data Index: 549625 (C4 (Web Text))

Max Activating Token Index: 503

Text #5

Max Range: 1.6192. Min Range: -1.6192

Max Act: 1.5018. Min Act: -0.0002

Data Index: 746947 (C4 (Web Text))

Max Activating Token Index: 72

Text #6

Max Range: 1.6192. Min Range: -1.6192

Max Act: 1.4353. Min Act: -0.0002

Data Index: 1101529 (C4 (Web Text))

Max Activating Token Index: 977

Text #7

Max Range: 1.6192. Min Range: -1.6192

Max Act: 1.3473. Min Act: -0.0002

Data Index: 378865 (C4 (Web Text))

Max Activating Token Index: 905

Text #8

Max Range: 1.6192. Min Range: -1.6192

Max Act: 1.3776. Min Act: -0.0002

Data Index: 807464 (C4 (Web Text))

Max Activating Token Index: 118

Text #9

Max Range: 1.6192. Min Range: -1.6192

Max Act: 1.4372. Min Act: -0.0002

Data Index: 819282 (C4 (Web Text))

Max Activating Token Index: 107

Text #10

Max Range: 1.6192. Min Range: -1.6192

Max Act: 1.4987. Min Act: -0.0002

Data Index: 1337502 (C4 (Web Text))

Max Activating Token Index: 867

Text #11

Max Range: 1.6192. Min Range: -1.6192

Max Act: 1.4777. Min Act: -0.0002

Data Index: 624751 (C4 (Web Text))

Max Activating Token Index: 799

Text #12

Max Range: 1.6192. Min Range: -1.6192

Max Act: 1.3863. Min Act: -0.0001

Data Index: 427809 (C4 (Web Text))

Max Activating Token Index: 436

Text #13

Max Range: 1.6192. Min Range: -1.6192

Max Act: 1.4066. Min Act: -0.0001

Data Index: 609635 (C4 (Web Text))

Max Activating Token Index: 588

Text #14

Max Range: 1.6192. Min Range: -1.6192

Max Act: 1.2700. Min Act: -0.0002

Data Index: 1060418 (C4 (Web Text))

Max Activating Token Index: 263

Text #15

Max Range: 1.6192. Min Range: -1.6192

Max Act: 1.3297. Min Act: -0.0002

Data Index: 1130567 (C4 (Web Text))

Max Activating Token Index: 550

Text #16

Max Range: 1.6192. Min Range: -1.6192

Max Act: 1.2642. Min Act: -0.0001

Data Index: 363826 (C4 (Web Text))

Max Activating Token Index: 83

Text #17

Max Range: 1.6192. Min Range: -1.6192

Max Act: 1.2860. Min Act: -0.0002

Data Index: 1240439 (C4 (Web Text))

Max Activating Token Index: 456

Text #18

Max Range: 1.6192. Min Range: -1.6192

Max Act: 1.3145. Min Act: -0.0002

Data Index: 283741 (C4 (Web Text))

Max Activating Token Index: 233

Text #19

Max Range: 1.6192. Min Range: -1.6192

Max Act: 1.2656. Min Act: -0.0001

Data Index: 233617 (C4 (Web Text))

Max Activating Token Index: 811