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

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

Neuron 183 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5859. Min Range: -1.5859

Max Act: 1.5859. Min Act: -0.0001

Data Index: 25269 (C4 (Web Text))

Max Activating Token Index: 407

Text #1

Max Range: 1.5859. Min Range: -1.5859

Max Act: 1.4263. Min Act: -0.0001

Data Index: 546607 (C4 (Web Text))

Max Activating Token Index: 118

Text #2

Max Range: 1.5859. Min Range: -1.5859

Max Act: 1.3837. Min Act: -0.0001

Data Index: 415492 (C4 (Web Text))

Max Activating Token Index: 967

Text #3

Max Range: 1.5859. Min Range: -1.5859

Max Act: 1.2321. Min Act: -0.0001

Data Index: 363533 (C4 (Web Text))

Max Activating Token Index: 844

Text #4

Max Range: 1.5859. Min Range: -1.5859

Max Act: 1.3076. Min Act: -0.0000

Data Index: 351117 (C4 (Web Text))

Max Activating Token Index: 196

Text #5

Max Range: 1.5859. Min Range: -1.5859

Max Act: 1.2669. Min Act: -0.0000

Data Index: 350616 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 1.5859. Min Range: -1.5859

Max Act: 1.2584. Min Act: -0.0001

Data Index: 935454 (C4 (Web Text))

Max Activating Token Index: 44

Text #7

Max Range: 1.5859. Min Range: -1.5859

Max Act: 1.2950. Min Act: -0.0001

Data Index: 1235989 (C4 (Web Text))

Max Activating Token Index: 29

Text #8

Max Range: 1.5859. Min Range: -1.5859

Max Act: 1.2434. Min Act: -0.0001

Data Index: 720845 (C4 (Web Text))

Max Activating Token Index: 263

Text #9

Max Range: 1.5859. Min Range: -1.5859

Max Act: 1.2317. Min Act: -0.0001

Data Index: 995622 (C4 (Web Text))

Max Activating Token Index: 458

Text #10

Max Range: 1.5859. Min Range: -1.5859

Max Act: 1.2321. Min Act: -0.0000

Data Index: 1035243 (C4 (Web Text))

Max Activating Token Index: 204

Text #11

Max Range: 1.5859. Min Range: -1.5859

Max Act: 1.2168. Min Act: -0.0001

Data Index: 1060924 (C4 (Web Text))

Max Activating Token Index: 47

Text #12

Max Range: 1.5859. Min Range: -1.5859

Max Act: 1.2434. Min Act: -0.0001

Data Index: 1141460 (C4 (Web Text))

Max Activating Token Index: 285

Text #13

Max Range: 1.5859. Min Range: -1.5859

Max Act: 1.1602. Min Act: -0.0001

Data Index: 1179537 (C4 (Web Text))

Max Activating Token Index: 210

Text #14

Max Range: 1.5859. Min Range: -1.5859

Max Act: 1.2004. Min Act: -0.0001

Data Index: 148777 (C4 (Web Text))

Max Activating Token Index: 251

Text #15

Max Range: 1.5859. Min Range: -1.5859

Max Act: 1.1645. Min Act: -0.0001

Data Index: 583185 (C4 (Web Text))

Max Activating Token Index: 405

Text #16

Max Range: 1.5859. Min Range: -1.5859

Max Act: 1.1518. Min Act: -0.0001

Data Index: 408460 (C4 (Web Text))

Max Activating Token Index: 118

Text #17

Max Range: 1.5859. Min Range: -1.5859

Max Act: 1.2102. Min Act: -0.0001

Data Index: 532088 (C4 (Web Text))

Max Activating Token Index: 1006

Text #18

Max Range: 1.5859. Min Range: -1.5859

Max Act: 1.0879. Min Act: -0.0000

Data Index: 1251455 (C4 (Web Text))

Max Activating Token Index: 926

Text #19

Max Range: 1.5859. Min Range: -1.5859

Max Act: 1.1499. Min Act: -0.0001

Data Index: 824991 (C4 (Web Text))

Max Activating Token Index: 808