Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2556 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.9681. Min Range: -2.9681

Max Act: 2.9681. Min Act: -0.0000

Data Index: 1136098 (C4 (Web Text))

Max Activating Token Index: 228

Text #1

Max Range: 2.9681. Min Range: -2.9681

Max Act: 2.9040. Min Act: -0.0000

Data Index: 568624 (C4 (Web Text))

Max Activating Token Index: 71

Text #2

Max Range: 2.9681. Min Range: -2.9681

Max Act: 2.7488. Min Act: -0.0000

Data Index: 585422 (C4 (Web Text))

Max Activating Token Index: 582

Text #3

Max Range: 2.9681. Min Range: -2.9681

Max Act: 2.8959. Min Act: -0.0000

Data Index: 43318 (C4 (Web Text))

Max Activating Token Index: 181

Text #4

Max Range: 2.9681. Min Range: -2.9681

Max Act: 2.5360. Min Act: -0.0000

Data Index: 258973 (C4 (Web Text))

Max Activating Token Index: 165

Text #5

Max Range: 2.9681. Min Range: -2.9681

Max Act: 2.3330. Min Act: -0.0000

Data Index: 1313571 (C4 (Web Text))

Max Activating Token Index: 591

Text #6

Max Range: 2.9681. Min Range: -2.9681

Max Act: 2.2580. Min Act: -0.0000

Data Index: 237710 (C4 (Web Text))

Max Activating Token Index: 746

Text #7

Max Range: 2.9681. Min Range: -2.9681

Max Act: 2.2461. Min Act: -0.0000

Data Index: 814264 (C4 (Web Text))

Max Activating Token Index: 473

Text #8

Max Range: 2.9681. Min Range: -2.9681

Max Act: 2.1955. Min Act: -0.0000

Data Index: 427207 (C4 (Web Text))

Max Activating Token Index: 73

Text #9

Max Range: 2.9681. Min Range: -2.9681

Max Act: 2.5226. Min Act: -0.0000

Data Index: 1239972 (C4 (Web Text))

Max Activating Token Index: 699

Text #10

Max Range: 2.9681. Min Range: -2.9681

Max Act: 2.0509. Min Act: -0.0000

Data Index: 1050715 (C4 (Web Text))

Max Activating Token Index: 466

Text #11

Max Range: 2.9681. Min Range: -2.9681

Max Act: 1.9854. Min Act: -0.0000

Data Index: 504984 (C4 (Web Text))

Max Activating Token Index: 837

Text #12

Max Range: 2.9681. Min Range: -2.9681

Max Act: 2.0882. Min Act: -0.0000

Data Index: 728181 (C4 (Web Text))

Max Activating Token Index: 931

Text #13

Max Range: 2.9681. Min Range: -2.9681

Max Act: 1.9334. Min Act: -0.0000

Data Index: 1003660 (C4 (Web Text))

Max Activating Token Index: 702

Text #14

Max Range: 2.9681. Min Range: -2.9681

Max Act: 2.0054. Min Act: -0.0000

Data Index: 1348104 (C4 (Web Text))

Max Activating Token Index: 82

Text #15

Max Range: 2.9681. Min Range: -2.9681

Max Act: 1.8906. Min Act: -0.0000

Data Index: 1073352 (C4 (Web Text))

Max Activating Token Index: 961

Text #16

Max Range: 2.9681. Min Range: -2.9681

Max Act: 1.9154. Min Act: -0.0000

Data Index: 674169 (C4 (Web Text))

Max Activating Token Index: 645

Text #17

Max Range: 2.9681. Min Range: -2.9681

Max Act: 1.9850. Min Act: -0.0000

Data Index: 63698 (C4 (Web Text))

Max Activating Token Index: 471

Text #18

Max Range: 2.9681. Min Range: -2.9681

Max Act: 1.6398. Min Act: -0.0000

Data Index: 216716 (C4 (Web Text))

Max Activating Token Index: 859

Text #19

Max Range: 2.9681. Min Range: -2.9681

Max Act: 2.0325. Min Act: -0.0000

Data Index: 37177 (C4 (Web Text))

Max Activating Token Index: 713