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

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

Neuron 2981 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6773. Min Range: -1.6773

Max Act: 1.6773. Min Act: -0.0001

Data Index: 737537 (C4 (Web Text))

Max Activating Token Index: 607

Text #1

Max Range: 1.6773. Min Range: -1.6773

Max Act: 1.5981. Min Act: -0.0001

Data Index: 176887 (C4 (Web Text))

Max Activating Token Index: 420

Text #2

Max Range: 1.6773. Min Range: -1.6773

Max Act: 1.6383. Min Act: -0.0001

Data Index: 165768 (C4 (Web Text))

Max Activating Token Index: 358

Text #3

Max Range: 1.6773. Min Range: -1.6773

Max Act: 1.6414. Min Act: -0.0001

Data Index: 1077174 (C4 (Web Text))

Max Activating Token Index: 986

Text #4

Max Range: 1.6773. Min Range: -1.6773

Max Act: 1.4644. Min Act: -0.0001

Data Index: 902252 (C4 (Web Text))

Max Activating Token Index: 927

Text #5

Max Range: 1.6773. Min Range: -1.6773

Max Act: 1.2461. Min Act: -0.0001

Data Index: 801555 (C4 (Web Text))

Max Activating Token Index: 921

Text #6

Max Range: 1.6773. Min Range: -1.6773

Max Act: 1.2666. Min Act: -0.0001

Data Index: 863623 (C4 (Web Text))

Max Activating Token Index: 1010

Text #7

Max Range: 1.6773. Min Range: -1.6773

Max Act: 1.3316. Min Act: -0.0001

Data Index: 236313 (C4 (Web Text))

Max Activating Token Index: 59

Text #8

Max Range: 1.6773. Min Range: -1.6773

Max Act: 1.3940. Min Act: -0.0001

Data Index: 535893 (C4 (Web Text))

Max Activating Token Index: 523

Text #9

Max Range: 1.6773. Min Range: -1.6773

Max Act: 1.2474. Min Act: -0.0001

Data Index: 371890 (C4 (Web Text))

Max Activating Token Index: 968

Text #10

Max Range: 1.6773. Min Range: -1.6773

Max Act: 1.1409. Min Act: -0.0001

Data Index: 1453 (C4 (Web Text))

Max Activating Token Index: 454

Text #11

Max Range: 1.6773. Min Range: -1.6773

Max Act: 1.2744. Min Act: -0.0001

Data Index: 489527 (C4 (Web Text))

Max Activating Token Index: 921

Text #12

Max Range: 1.6773. Min Range: -1.6773

Max Act: 1.2990. Min Act: -0.0001

Data Index: 732403 (C4 (Web Text))

Max Activating Token Index: 812

Text #13

Max Range: 1.6773. Min Range: -1.6773

Max Act: 1.2239. Min Act: -0.0001

Data Index: 686824 (C4 (Web Text))

Max Activating Token Index: 859

Text #14

Max Range: 1.6773. Min Range: -1.6773

Max Act: 1.1173. Min Act: -0.0001

Data Index: 56180 (C4 (Web Text))

Max Activating Token Index: 782

Text #15

Max Range: 1.6773. Min Range: -1.6773

Max Act: 1.2037. Min Act: -0.0001

Data Index: 365065 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 1.6773. Min Range: -1.6773

Max Act: 1.2598. Min Act: -0.0001

Data Index: 909204 (C4 (Web Text))

Max Activating Token Index: 839

Text #17

Max Range: 1.6773. Min Range: -1.6773

Max Act: 1.0872. Min Act: -0.0001

Data Index: 216023 (C4 (Web Text))

Max Activating Token Index: 81

Text #18

Max Range: 1.6773. Min Range: -1.6773

Max Act: 1.0134. Min Act: -0.0001

Data Index: 786810 (C4 (Web Text))

Max Activating Token Index: 629

Text #19

Max Range: 1.6773. Min Range: -1.6773

Max Act: 1.1514. Min Act: -0.0001

Data Index: 1319774 (C4 (Web Text))

Max Activating Token Index: 460