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

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

Neuron 2882 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2121. Min Range: -1.2121

Max Act: 1.2121. Min Act: -0.0000

Data Index: 764467 (C4 (Web Text))

Max Activating Token Index: 921

Text #1

Max Range: 1.2121. Min Range: -1.2121

Max Act: 1.0972. Min Act: -0.0000

Data Index: 765891 (C4 (Web Text))

Max Activating Token Index: 112

Text #2

Max Range: 1.2121. Min Range: -1.2121

Max Act: 1.1052. Min Act: -0.0000

Data Index: 308760 (C4 (Web Text))

Max Activating Token Index: 112

Text #3

Max Range: 1.2121. Min Range: -1.2121

Max Act: 0.8908. Min Act: -0.0000

Data Index: 33758 (C4 (Web Text))

Max Activating Token Index: 144

Text #4

Max Range: 1.2121. Min Range: -1.2121

Max Act: 0.9006. Min Act: -0.0000

Data Index: 515430 (C4 (Web Text))

Max Activating Token Index: 48

Text #5

Max Range: 1.2121. Min Range: -1.2121

Max Act: 0.8688. Min Act: -0.0000

Data Index: 444278 (C4 (Web Text))

Max Activating Token Index: 70

Text #6

Max Range: 1.2121. Min Range: -1.2121

Max Act: 0.8627. Min Act: -0.0000

Data Index: 1296258 (C4 (Web Text))

Max Activating Token Index: 41

Text #7

Max Range: 1.2121. Min Range: -1.2121

Max Act: 0.8960. Min Act: -0.0000

Data Index: 335332 (C4 (Web Text))

Max Activating Token Index: 555

Text #8

Max Range: 1.2121. Min Range: -1.2121

Max Act: 0.8704. Min Act: -0.0000

Data Index: 1192811 (C4 (Web Text))

Max Activating Token Index: 51

Text #9

Max Range: 1.2121. Min Range: -1.2121

Max Act: 0.8945. Min Act: -0.0000

Data Index: 1107724 (C4 (Web Text))

Max Activating Token Index: 844

Text #10

Max Range: 1.2121. Min Range: -1.2121

Max Act: 0.8276. Min Act: -0.0000

Data Index: 879048 (C4 (Web Text))

Max Activating Token Index: 38

Text #11

Max Range: 1.2121. Min Range: -1.2121

Max Act: 0.8185. Min Act: -0.0000

Data Index: 770661 (C4 (Web Text))

Max Activating Token Index: 995

Text #12

Max Range: 1.2121. Min Range: -1.2121

Max Act: 0.7966. Min Act: -0.0000

Data Index: 872725 (C4 (Web Text))

Max Activating Token Index: 865

Text #13

Max Range: 1.2121. Min Range: -1.2121

Max Act: 0.8214. Min Act: -0.0000

Data Index: 1343464 (C4 (Web Text))

Max Activating Token Index: 67

Text #14

Max Range: 1.2121. Min Range: -1.2121

Max Act: 0.8350. Min Act: -0.0000

Data Index: 1522710 (Python Code)

Max Activating Token Index: 418

Text #15

Max Range: 1.2121. Min Range: -1.2121

Max Act: 0.8778. Min Act: -0.0000

Data Index: 868308 (C4 (Web Text))

Max Activating Token Index: 209

Text #16

Max Range: 1.2121. Min Range: -1.2121

Max Act: 0.7767. Min Act: -0.0000

Data Index: 1310742 (C4 (Web Text))

Max Activating Token Index: 712

Text #17

Max Range: 1.2121. Min Range: -1.2121

Max Act: 0.7770. Min Act: -0.0000

Data Index: 600084 (C4 (Web Text))

Max Activating Token Index: 243

Text #18

Max Range: 1.2121. Min Range: -1.2121

Max Act: 0.8223. Min Act: -0.0000

Data Index: 152750 (C4 (Web Text))

Max Activating Token Index: 204

Text #19

Max Range: 1.2121. Min Range: -1.2121

Max Act: 0.7854. Min Act: -0.0000

Data Index: 1056822 (C4 (Web Text))

Max Activating Token Index: 848