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

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

Neuron 1598 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: 2.9673. Min Range: -2.9673

Max Act: 2.9673. Min Act: -0.0000

Data Index: 185506 (C4 (Web Text))

Max Activating Token Index: 568

Text #1

Max Range: 2.9673. Min Range: -2.9673

Max Act: 2.4205. Min Act: -0.0000

Data Index: 1262903 (C4 (Web Text))

Max Activating Token Index: 31

Text #2

Max Range: 2.9673. Min Range: -2.9673

Max Act: 2.3704. Min Act: -0.0000

Data Index: 948294 (C4 (Web Text))

Max Activating Token Index: 891

Text #3

Max Range: 2.9673. Min Range: -2.9673

Max Act: 2.2100. Min Act: -0.0000

Data Index: 561275 (C4 (Web Text))

Max Activating Token Index: 52

Text #4

Max Range: 2.9673. Min Range: -2.9673

Max Act: 2.2825. Min Act: -0.0000

Data Index: 1346260 (C4 (Web Text))

Max Activating Token Index: 816

Text #5

Max Range: 2.9673. Min Range: -2.9673

Max Act: 2.1957. Min Act: -0.0000

Data Index: 1027068 (C4 (Web Text))

Max Activating Token Index: 136

Text #6

Max Range: 2.9673. Min Range: -2.9673

Max Act: 2.3074. Min Act: -0.0000

Data Index: 649545 (C4 (Web Text))

Max Activating Token Index: 587

Text #7

Max Range: 2.9673. Min Range: -2.9673

Max Act: 2.0469. Min Act: -0.0000

Data Index: 318270 (C4 (Web Text))

Max Activating Token Index: 324

Text #8

Max Range: 2.9673. Min Range: -2.9673

Max Act: 2.0326. Min Act: -0.0000

Data Index: 1080893 (C4 (Web Text))

Max Activating Token Index: 599

Text #9

Max Range: 2.9673. Min Range: -2.9673

Max Act: 2.1419. Min Act: -0.0000

Data Index: 969862 (C4 (Web Text))

Max Activating Token Index: 587

Text #10

Max Range: 2.9673. Min Range: -2.9673

Max Act: 2.1029. Min Act: -0.0000

Data Index: 1035737 (C4 (Web Text))

Max Activating Token Index: 458

Text #11

Max Range: 2.9673. Min Range: -2.9673

Max Act: 2.1047. Min Act: -0.0000

Data Index: 501325 (C4 (Web Text))

Max Activating Token Index: 317

Text #12

Max Range: 2.9673. Min Range: -2.9673

Max Act: 2.1097. Min Act: -0.0000

Data Index: 464378 (C4 (Web Text))

Max Activating Token Index: 703

Text #13

Max Range: 2.9673. Min Range: -2.9673

Max Act: 2.1058. Min Act: -0.0000

Data Index: 1290277 (C4 (Web Text))

Max Activating Token Index: 948

Text #14

Max Range: 2.9673. Min Range: -2.9673

Max Act: 2.0960. Min Act: -0.0000

Data Index: 1290519 (C4 (Web Text))

Max Activating Token Index: 306

Text #15

Max Range: 2.9673. Min Range: -2.9673

Max Act: 2.0789. Min Act: -0.0000

Data Index: 326763 (C4 (Web Text))

Max Activating Token Index: 900

Text #16

Max Range: 2.9673. Min Range: -2.9673

Max Act: 1.9179. Min Act: -0.0000

Data Index: 269619 (C4 (Web Text))

Max Activating Token Index: 939

Text #17

Max Range: 2.9673. Min Range: -2.9673

Max Act: 2.1346. Min Act: -0.0000

Data Index: 285236 (C4 (Web Text))

Max Activating Token Index: 237

Text #18

Max Range: 2.9673. Min Range: -2.9673

Max Act: 2.0119. Min Act: -0.0000

Data Index: 678165 (C4 (Web Text))

Max Activating Token Index: 608

Text #19

Max Range: 2.9673. Min Range: -2.9673

Max Act: 1.9857. Min Act: -0.0000

Data Index: 407542 (C4 (Web Text))

Max Activating Token Index: 798