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

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

Neuron 870 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6656. Min Range: -4.6656

Max Act: 4.6656. Min Act: -0.0000

Data Index: 199333 (C4 (Web Text))

Max Activating Token Index: 902

Text #1

Max Range: 4.6656. Min Range: -4.6656

Max Act: 4.4004. Min Act: -0.0000

Data Index: 995155 (C4 (Web Text))

Max Activating Token Index: 980

Text #2

Max Range: 4.6656. Min Range: -4.6656

Max Act: 4.0344. Min Act: -0.0000

Data Index: 1095430 (C4 (Web Text))

Max Activating Token Index: 950

Text #3

Max Range: 4.6656. Min Range: -4.6656

Max Act: 4.1092. Min Act: -0.0000

Data Index: 280229 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 4.6656. Min Range: -4.6656

Max Act: 4.1970. Min Act: -0.0000

Data Index: 1228345 (C4 (Web Text))

Max Activating Token Index: 951

Text #5

Max Range: 4.6656. Min Range: -4.6656

Max Act: 3.8545. Min Act: -0.0000

Data Index: 944496 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 4.6656. Min Range: -4.6656

Max Act: 3.8595. Min Act: -0.0000

Data Index: 822661 (C4 (Web Text))

Max Activating Token Index: 188

Text #7

Max Range: 4.6656. Min Range: -4.6656

Max Act: 3.5934. Min Act: -0.0000

Data Index: 1185393 (C4 (Web Text))

Max Activating Token Index: 656

Text #8

Max Range: 4.6656. Min Range: -4.6656

Max Act: 3.5094. Min Act: -0.0000

Data Index: 728977 (C4 (Web Text))

Max Activating Token Index: 728

Text #9

Max Range: 4.6656. Min Range: -4.6656

Max Act: 3.4225. Min Act: -0.0000

Data Index: 679441 (C4 (Web Text))

Max Activating Token Index: 54

Text #10

Max Range: 4.6656. Min Range: -4.6656

Max Act: 3.3851. Min Act: -0.0000

Data Index: 1034622 (C4 (Web Text))

Max Activating Token Index: 786

Text #11

Max Range: 4.6656. Min Range: -4.6656

Max Act: 3.2689. Min Act: -0.0000

Data Index: 428891 (C4 (Web Text))

Max Activating Token Index: 819

Text #12

Max Range: 4.6656. Min Range: -4.6656

Max Act: 3.2581. Min Act: -0.0000

Data Index: 943082 (C4 (Web Text))

Max Activating Token Index: 407

Text #13

Max Range: 4.6656. Min Range: -4.6656

Max Act: 3.2078. Min Act: -0.0000

Data Index: 1142073 (C4 (Web Text))

Max Activating Token Index: 318

Text #14

Max Range: 4.6656. Min Range: -4.6656

Max Act: 2.8828. Min Act: -0.0000

Data Index: 1282986 (C4 (Web Text))

Max Activating Token Index: 637

Text #15

Max Range: 4.6656. Min Range: -4.6656

Max Act: 3.3263. Min Act: -0.0000

Data Index: 1347442 (C4 (Web Text))

Max Activating Token Index: 790

Text #16

Max Range: 4.6656. Min Range: -4.6656

Max Act: 3.1661. Min Act: -0.0000

Data Index: 278973 (C4 (Web Text))

Max Activating Token Index: 393

Text #17

Max Range: 4.6656. Min Range: -4.6656

Max Act: 3.0074. Min Act: -0.0000

Data Index: 1169538 (C4 (Web Text))

Max Activating Token Index: 925

Text #18

Max Range: 4.6656. Min Range: -4.6656

Max Act: 3.1438. Min Act: -0.0000

Data Index: 363716 (C4 (Web Text))

Max Activating Token Index: 100

Text #19

Max Range: 4.6656. Min Range: -4.6656

Max Act: 2.9809. Min Act: -0.0000

Data Index: 17839 (C4 (Web Text))

Max Activating Token Index: 166