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

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

Neuron 4081 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.7979. Min Range: -7.7979

Max Act: 7.7979. Min Act: -0.0001

Data Index: 845456 (C4 (Web Text))

Max Activating Token Index: 429

Text #1

Max Range: 7.7979. Min Range: -7.7979

Max Act: 7.7679. Min Act: -0.0001

Data Index: 523886 (C4 (Web Text))

Max Activating Token Index: 948

Text #2

Max Range: 7.7979. Min Range: -7.7979

Max Act: 7.4256. Min Act: -0.0001

Data Index: 553781 (C4 (Web Text))

Max Activating Token Index: 642

Text #3

Max Range: 7.7979. Min Range: -7.7979

Max Act: 7.0935. Min Act: -0.0001

Data Index: 520534 (C4 (Web Text))

Max Activating Token Index: 910

Text #4

Max Range: 7.7979. Min Range: -7.7979

Max Act: 7.4016. Min Act: -0.0001

Data Index: 346292 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 7.7979. Min Range: -7.7979

Max Act: 7.3188. Min Act: -0.0001

Data Index: 1354097 (C4 (Web Text))

Max Activating Token Index: 17

Text #6

Max Range: 7.7979. Min Range: -7.7979

Max Act: 7.6175. Min Act: -0.0001

Data Index: 71664 (C4 (Web Text))

Max Activating Token Index: 497

Text #7

Max Range: 7.7979. Min Range: -7.7979

Max Act: 7.2600. Min Act: -0.0001

Data Index: 1032101 (C4 (Web Text))

Max Activating Token Index: 27

Text #8

Max Range: 7.7979. Min Range: -7.7979

Max Act: 7.5695. Min Act: -0.0001

Data Index: 301141 (C4 (Web Text))

Max Activating Token Index: 914

Text #9

Max Range: 7.7979. Min Range: -7.7979

Max Act: 7.5685. Min Act: -0.0001

Data Index: 583903 (C4 (Web Text))

Max Activating Token Index: 93

Text #10

Max Range: 7.7979. Min Range: -7.7979

Max Act: 7.2280. Min Act: -0.0001

Data Index: 370952 (C4 (Web Text))

Max Activating Token Index: 1005

Text #11

Max Range: 7.7979. Min Range: -7.7979

Max Act: 7.2109. Min Act: -0.0001

Data Index: 6565 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 7.7979. Min Range: -7.7979

Max Act: 7.2614. Min Act: -0.0001

Data Index: 107210 (C4 (Web Text))

Max Activating Token Index: 902

Text #13

Max Range: 7.7979. Min Range: -7.7979

Max Act: 7.0876. Min Act: -0.0001

Data Index: 1256015 (C4 (Web Text))

Max Activating Token Index: 813

Text #14

Max Range: 7.7979. Min Range: -7.7979

Max Act: 6.7481. Min Act: -0.0001

Data Index: 533019 (C4 (Web Text))

Max Activating Token Index: 77

Text #15

Max Range: 7.7979. Min Range: -7.7979

Max Act: 7.2289. Min Act: -0.0001

Data Index: 1210906 (C4 (Web Text))

Max Activating Token Index: 560

Text #16

Max Range: 7.7979. Min Range: -7.7979

Max Act: 7.0300. Min Act: -0.0001

Data Index: 849152 (C4 (Web Text))

Max Activating Token Index: 873

Text #17

Max Range: 7.7979. Min Range: -7.7979

Max Act: 7.1290. Min Act: -0.0001

Data Index: 293284 (C4 (Web Text))

Max Activating Token Index: 344

Text #18

Max Range: 7.7979. Min Range: -7.7979

Max Act: 6.8067. Min Act: -0.0001

Data Index: 118054 (C4 (Web Text))

Max Activating Token Index: 180

Text #19

Max Range: 7.7979. Min Range: -7.7979

Max Act: 7.2960. Min Act: -0.0001

Data Index: 403947 (C4 (Web Text))

Max Activating Token Index: 646