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

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

Neuron 3451 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3875. Min Range: -0.3875

Max Act: 0.3875. Min Act: -0.0001

Data Index: 146394 (C4 (Web Text))

Max Activating Token Index: 549

Text #1

Max Range: 0.3875. Min Range: -0.3875

Max Act: 0.2926. Min Act: -0.0001

Data Index: 176069 (C4 (Web Text))

Max Activating Token Index: 550

Text #2

Max Range: 0.3875. Min Range: -0.3875

Max Act: 0.2871. Min Act: -0.0001

Data Index: 931359 (C4 (Web Text))

Max Activating Token Index: 156

Text #3

Max Range: 0.3875. Min Range: -0.3875

Max Act: 0.2938. Min Act: -0.0001

Data Index: 206143 (C4 (Web Text))

Max Activating Token Index: 175

Text #4

Max Range: 0.3875. Min Range: -0.3875

Max Act: 0.2837. Min Act: -0.0001

Data Index: 1221634 (C4 (Web Text))

Max Activating Token Index: 383

Text #5

Max Range: 0.3875. Min Range: -0.3875

Max Act: 0.2631. Min Act: -0.0001

Data Index: 1066814 (C4 (Web Text))

Max Activating Token Index: 770

Text #6

Max Range: 0.3875. Min Range: -0.3875

Max Act: 0.2457. Min Act: -0.0001

Data Index: 828080 (C4 (Web Text))

Max Activating Token Index: 506

Text #7

Max Range: 0.3875. Min Range: -0.3875

Max Act: 0.2715. Min Act: -0.0001

Data Index: 1300134 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 0.3875. Min Range: -0.3875

Max Act: 0.2520. Min Act: -0.0001

Data Index: 1341255 (C4 (Web Text))

Max Activating Token Index: 179

Text #9

Max Range: 0.3875. Min Range: -0.3875

Max Act: 0.2338. Min Act: -0.0001

Data Index: 862384 (C4 (Web Text))

Max Activating Token Index: 306

Text #10

Max Range: 0.3875. Min Range: -0.3875

Max Act: 0.2394. Min Act: -0.0001

Data Index: 163933 (C4 (Web Text))

Max Activating Token Index: 890

Text #11

Max Range: 0.3875. Min Range: -0.3875

Max Act: 0.2475. Min Act: -0.0001

Data Index: 1004204 (C4 (Web Text))

Max Activating Token Index: 673

Text #12

Max Range: 0.3875. Min Range: -0.3875

Max Act: 0.2363. Min Act: -0.0001

Data Index: 187731 (C4 (Web Text))

Max Activating Token Index: 90

Text #13

Max Range: 0.3875. Min Range: -0.3875

Max Act: 0.2203. Min Act: -0.0001

Data Index: 1067483 (C4 (Web Text))

Max Activating Token Index: 583

Text #14

Max Range: 0.3875. Min Range: -0.3875

Max Act: 0.2061. Min Act: -0.0001

Data Index: 62105 (C4 (Web Text))

Max Activating Token Index: 689

Text #15

Max Range: 0.3875. Min Range: -0.3875

Max Act: 0.2174. Min Act: -0.0001

Data Index: 796928 (C4 (Web Text))

Max Activating Token Index: 393

Text #16

Max Range: 0.3875. Min Range: -0.3875

Max Act: 0.2238. Min Act: -0.0001

Data Index: 1049733 (C4 (Web Text))

Max Activating Token Index: 851

Text #17

Max Range: 0.3875. Min Range: -0.3875

Max Act: 0.2422. Min Act: -0.0001

Data Index: 128631 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 0.3875. Min Range: -0.3875

Max Act: 0.2196. Min Act: -0.0001

Data Index: 966615 (C4 (Web Text))

Max Activating Token Index: 533

Text #19

Max Range: 0.3875. Min Range: -0.3875

Max Act: 0.2345. Min Act: -0.0001

Data Index: 1351102 (C4 (Web Text))

Max Activating Token Index: 361