Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3856 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.9079. Min Range: -5.9079

Max Act: 5.9079. Min Act: -0.0001

Data Index: 217041 (C4 (Web Text))

Max Activating Token Index: 777

Text #1

Max Range: 5.9079. Min Range: -5.9079

Max Act: 5.5792. Min Act: -0.0001

Data Index: 1320750 (C4 (Web Text))

Max Activating Token Index: 146

Text #2

Max Range: 5.9079. Min Range: -5.9079

Max Act: 5.1664. Min Act: -0.0001

Data Index: 502510 (C4 (Web Text))

Max Activating Token Index: 114

Text #3

Max Range: 5.9079. Min Range: -5.9079

Max Act: 4.5931. Min Act: -0.0001

Data Index: 1136888 (C4 (Web Text))

Max Activating Token Index: 938

Text #4

Max Range: 5.9079. Min Range: -5.9079

Max Act: 4.1234. Min Act: -0.0001

Data Index: 800526 (C4 (Web Text))

Max Activating Token Index: 10

Text #5

Max Range: 5.9079. Min Range: -5.9079

Max Act: 4.1114. Min Act: -0.0001

Data Index: 1104426 (C4 (Web Text))

Max Activating Token Index: 157

Text #6

Max Range: 5.9079. Min Range: -5.9079

Max Act: 3.9480. Min Act: -0.0001

Data Index: 269789 (C4 (Web Text))

Max Activating Token Index: 146

Text #7

Max Range: 5.9079. Min Range: -5.9079

Max Act: 3.9189. Min Act: -0.0001

Data Index: 1065792 (C4 (Web Text))

Max Activating Token Index: 282

Text #8

Max Range: 5.9079. Min Range: -5.9079

Max Act: 4.0200. Min Act: -0.0001

Data Index: 132144 (C4 (Web Text))

Max Activating Token Index: 98

Text #9

Max Range: 5.9079. Min Range: -5.9079

Max Act: 3.9560. Min Act: -0.0001

Data Index: 673493 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 5.9079. Min Range: -5.9079

Max Act: 3.8280. Min Act: -0.0001

Data Index: 28744 (C4 (Web Text))

Max Activating Token Index: 453

Text #11

Max Range: 5.9079. Min Range: -5.9079

Max Act: 3.9034. Min Act: -0.0001

Data Index: 649788 (C4 (Web Text))

Max Activating Token Index: 391

Text #12

Max Range: 5.9079. Min Range: -5.9079

Max Act: 3.7867. Min Act: -0.0001

Data Index: 1094165 (C4 (Web Text))

Max Activating Token Index: 39

Text #13

Max Range: 5.9079. Min Range: -5.9079

Max Act: 3.2653. Min Act: -0.0001

Data Index: 331164 (C4 (Web Text))

Max Activating Token Index: 974

Text #14

Max Range: 5.9079. Min Range: -5.9079

Max Act: 3.9008. Min Act: -0.0001

Data Index: 423313 (C4 (Web Text))

Max Activating Token Index: 860

Text #15

Max Range: 5.9079. Min Range: -5.9079

Max Act: 3.5695. Min Act: -0.0001

Data Index: 1289667 (C4 (Web Text))

Max Activating Token Index: 614

Text #16

Max Range: 5.9079. Min Range: -5.9079

Max Act: 3.3059. Min Act: -0.0001

Data Index: 422135 (C4 (Web Text))

Max Activating Token Index: 372

Text #17

Max Range: 5.9079. Min Range: -5.9079

Max Act: 3.7088. Min Act: -0.0001

Data Index: 1146609 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 5.9079. Min Range: -5.9079

Max Act: 3.3797. Min Act: -0.0001

Data Index: 973398 (C4 (Web Text))

Max Activating Token Index: 8

Text #19

Max Range: 5.9079. Min Range: -5.9079

Max Act: 3.1520. Min Act: -0.0001

Data Index: 957443 (C4 (Web Text))

Max Activating Token Index: 32