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

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

Neuron 3565 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: 2.2997. Min Range: -2.2997

Max Act: 2.2997. Min Act: -0.0000

Data Index: 1169529 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 2.2997. Min Range: -2.2997

Max Act: 2.1649. Min Act: -0.0000

Data Index: 696726 (C4 (Web Text))

Max Activating Token Index: 557

Text #2

Max Range: 2.2997. Min Range: -2.2997

Max Act: 2.0560. Min Act: -0.0000

Data Index: 432696 (C4 (Web Text))

Max Activating Token Index: 819

Text #3

Max Range: 2.2997. Min Range: -2.2997

Max Act: 2.1274. Min Act: -0.0000

Data Index: 1294657 (C4 (Web Text))

Max Activating Token Index: 501

Text #4

Max Range: 2.2997. Min Range: -2.2997

Max Act: 1.6532. Min Act: -0.0000

Data Index: 514465 (C4 (Web Text))

Max Activating Token Index: 843

Text #5

Max Range: 2.2997. Min Range: -2.2997

Max Act: 2.0068. Min Act: -0.0000

Data Index: 364948 (C4 (Web Text))

Max Activating Token Index: 367

Text #6

Max Range: 2.2997. Min Range: -2.2997

Max Act: 1.7959. Min Act: -0.0000

Data Index: 66094 (C4 (Web Text))

Max Activating Token Index: 137

Text #7

Max Range: 2.2997. Min Range: -2.2997

Max Act: 1.6858. Min Act: -0.0000

Data Index: 1029624 (C4 (Web Text))

Max Activating Token Index: 548

Text #8

Max Range: 2.2997. Min Range: -2.2997

Max Act: 1.8865. Min Act: -0.0000

Data Index: 1021773 (C4 (Web Text))

Max Activating Token Index: 790

Text #9

Max Range: 2.2997. Min Range: -2.2997

Max Act: 1.7706. Min Act: -0.0000

Data Index: 903382 (C4 (Web Text))

Max Activating Token Index: 951

Text #10

Max Range: 2.2997. Min Range: -2.2997

Max Act: 1.7611. Min Act: -0.0000

Data Index: 1061654 (C4 (Web Text))

Max Activating Token Index: 192

Text #11

Max Range: 2.2997. Min Range: -2.2997

Max Act: 1.6310. Min Act: -0.0000

Data Index: 1182131 (C4 (Web Text))

Max Activating Token Index: 883

Text #12

Max Range: 2.2997. Min Range: -2.2997

Max Act: 1.6219. Min Act: -0.0000

Data Index: 263863 (C4 (Web Text))

Max Activating Token Index: 354

Text #13

Max Range: 2.2997. Min Range: -2.2997

Max Act: 1.7085. Min Act: -0.0000

Data Index: 370463 (C4 (Web Text))

Max Activating Token Index: 765

Text #14

Max Range: 2.2997. Min Range: -2.2997

Max Act: 1.6057. Min Act: -0.0000

Data Index: 253411 (C4 (Web Text))

Max Activating Token Index: 863

Text #15

Max Range: 2.2997. Min Range: -2.2997

Max Act: 1.6724. Min Act: -0.0000

Data Index: 1183207 (C4 (Web Text))

Max Activating Token Index: 767

Text #16

Max Range: 2.2997. Min Range: -2.2997

Max Act: 1.6626. Min Act: -0.0000

Data Index: 1352137 (C4 (Web Text))

Max Activating Token Index: 1004

Text #17

Max Range: 2.2997. Min Range: -2.2997

Max Act: 1.4033. Min Act: -0.0000

Data Index: 797648 (C4 (Web Text))

Max Activating Token Index: 695

Text #18

Max Range: 2.2997. Min Range: -2.2997

Max Act: 1.5524. Min Act: -0.0000

Data Index: 1150511 (C4 (Web Text))

Max Activating Token Index: 112

Text #19

Max Range: 2.2997. Min Range: -2.2997

Max Act: 1.5409. Min Act: -0.0000

Data Index: 395422 (C4 (Web Text))

Max Activating Token Index: 995