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

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

Neuron 1999 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3329. Min Range: -1.3329

Max Act: 1.3329. Min Act: -0.0000

Data Index: 1270250 (C4 (Web Text))

Max Activating Token Index: 649

Text #1

Max Range: 1.3329. Min Range: -1.3329

Max Act: 1.0807. Min Act: -0.0001

Data Index: 183352 (C4 (Web Text))

Max Activating Token Index: 660

Text #2

Max Range: 1.3329. Min Range: -1.3329

Max Act: 0.8908. Min Act: -0.0000

Data Index: 210030 (C4 (Web Text))

Max Activating Token Index: 1015

Text #3

Max Range: 1.3329. Min Range: -1.3329

Max Act: 0.9418. Min Act: -0.0000

Data Index: 912979 (C4 (Web Text))

Max Activating Token Index: 425

Text #4

Max Range: 1.3329. Min Range: -1.3329

Max Act: 0.9086. Min Act: -0.0001

Data Index: 781986 (C4 (Web Text))

Max Activating Token Index: 535

Text #5

Max Range: 1.3329. Min Range: -1.3329

Max Act: 0.8573. Min Act: -0.0000

Data Index: 1208232 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 1.3329. Min Range: -1.3329

Max Act: 0.8269. Min Act: -0.0000

Data Index: 93191 (C4 (Web Text))

Max Activating Token Index: 467

Text #7

Max Range: 1.3329. Min Range: -1.3329

Max Act: 0.8974. Min Act: -0.0000

Data Index: 319799 (C4 (Web Text))

Max Activating Token Index: 232

Text #8

Max Range: 1.3329. Min Range: -1.3329

Max Act: 0.8435. Min Act: -0.0000

Data Index: 511889 (C4 (Web Text))

Max Activating Token Index: 123

Text #9

Max Range: 1.3329. Min Range: -1.3329

Max Act: 0.8156. Min Act: -0.0000

Data Index: 58548 (C4 (Web Text))

Max Activating Token Index: 368

Text #10

Max Range: 1.3329. Min Range: -1.3329

Max Act: 0.8365. Min Act: -0.0000

Data Index: 494436 (C4 (Web Text))

Max Activating Token Index: 635

Text #11

Max Range: 1.3329. Min Range: -1.3329

Max Act: 0.8052. Min Act: -0.0000

Data Index: 1186790 (C4 (Web Text))

Max Activating Token Index: 510

Text #12

Max Range: 1.3329. Min Range: -1.3329

Max Act: 0.8271. Min Act: -0.0000

Data Index: 600550 (C4 (Web Text))

Max Activating Token Index: 280

Text #13

Max Range: 1.3329. Min Range: -1.3329

Max Act: 0.8167. Min Act: -0.0000

Data Index: 691602 (C4 (Web Text))

Max Activating Token Index: 930

Text #14

Max Range: 1.3329. Min Range: -1.3329

Max Act: 0.7936. Min Act: -0.0000

Data Index: 234104 (C4 (Web Text))

Max Activating Token Index: 720

Text #15

Max Range: 1.3329. Min Range: -1.3329

Max Act: 0.7606. Min Act: -0.0001

Data Index: 941948 (C4 (Web Text))

Max Activating Token Index: 192

Text #16

Max Range: 1.3329. Min Range: -1.3329

Max Act: 0.7563. Min Act: -0.0000

Data Index: 972941 (C4 (Web Text))

Max Activating Token Index: 653

Text #17

Max Range: 1.3329. Min Range: -1.3329

Max Act: 0.7908. Min Act: -0.0000

Data Index: 1258120 (C4 (Web Text))

Max Activating Token Index: 960

Text #18

Max Range: 1.3329. Min Range: -1.3329

Max Act: 0.7996. Min Act: -0.0000

Data Index: 814589 (C4 (Web Text))

Max Activating Token Index: 774

Text #19

Max Range: 1.3329. Min Range: -1.3329

Max Act: 0.7722. Min Act: -0.0001

Data Index: 549174 (C4 (Web Text))

Max Activating Token Index: 936