Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 32 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.7038. Min Range: -1.7038

Max Act: 1.6748. Min Act: -0.0001

Data Index: 1013658 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 1.7038. Min Range: -1.7038

Max Act: 1.7038. Min Act: -0.0001

Data Index: 1133005 (C4 (Web Text))

Max Activating Token Index: 241

Text #2

Max Range: 1.7038. Min Range: -1.7038

Max Act: 1.7018. Min Act: -0.0001

Data Index: 1001285 (C4 (Web Text))

Max Activating Token Index: 733

Text #3

Max Range: 1.7038. Min Range: -1.7038

Max Act: 1.6018. Min Act: -0.0001

Data Index: 425290 (C4 (Web Text))

Max Activating Token Index: 421

Text #4

Max Range: 1.7038. Min Range: -1.7038

Max Act: 1.4701. Min Act: -0.0001

Data Index: 869958 (C4 (Web Text))

Max Activating Token Index: 855

Text #5

Max Range: 1.7038. Min Range: -1.7038

Max Act: 1.6327. Min Act: -0.0001

Data Index: 571450 (C4 (Web Text))

Max Activating Token Index: 127

Text #6

Max Range: 1.7038. Min Range: -1.7038

Max Act: 1.4916. Min Act: -0.0001

Data Index: 190870 (C4 (Web Text))

Max Activating Token Index: 151

Text #7

Max Range: 1.7038. Min Range: -1.7038

Max Act: 1.5077. Min Act: -0.0001

Data Index: 555385 (C4 (Web Text))

Max Activating Token Index: 872

Text #8

Max Range: 1.7038. Min Range: -1.7038

Max Act: 1.5072. Min Act: -0.0001

Data Index: 408139 (C4 (Web Text))

Max Activating Token Index: 487

Text #9

Max Range: 1.7038. Min Range: -1.7038

Max Act: 1.4093. Min Act: -0.0001

Data Index: 370056 (C4 (Web Text))

Max Activating Token Index: 709

Text #10

Max Range: 1.7038. Min Range: -1.7038

Max Act: 1.4972. Min Act: -0.0001

Data Index: 921971 (C4 (Web Text))

Max Activating Token Index: 945

Text #11

Max Range: 1.7038. Min Range: -1.7038

Max Act: 1.4502. Min Act: -0.0001

Data Index: 1046621 (C4 (Web Text))

Max Activating Token Index: 716

Text #12

Max Range: 1.7038. Min Range: -1.7038

Max Act: 1.4871. Min Act: -0.0001

Data Index: 165669 (C4 (Web Text))

Max Activating Token Index: 1016

Text #13

Max Range: 1.7038. Min Range: -1.7038

Max Act: 1.4834. Min Act: -0.0001

Data Index: 412946 (C4 (Web Text))

Max Activating Token Index: 519

Text #14

Max Range: 1.7038. Min Range: -1.7038

Max Act: 1.4727. Min Act: -0.0001

Data Index: 566877 (C4 (Web Text))

Max Activating Token Index: 491

Text #15

Max Range: 1.7038. Min Range: -1.7038

Max Act: 1.5237. Min Act: -0.0001

Data Index: 777663 (C4 (Web Text))

Max Activating Token Index: 627

Text #16

Max Range: 1.7038. Min Range: -1.7038

Max Act: 1.4299. Min Act: -0.0001

Data Index: 550300 (C4 (Web Text))

Max Activating Token Index: 413

Text #17

Max Range: 1.7038. Min Range: -1.7038

Max Act: 1.4626. Min Act: -0.0001

Data Index: 562057 (C4 (Web Text))

Max Activating Token Index: 170

Text #18

Max Range: 1.7038. Min Range: -1.7038

Max Act: 1.4473. Min Act: -0.0001

Data Index: 1164684 (C4 (Web Text))

Max Activating Token Index: 917

Text #19

Max Range: 1.7038. Min Range: -1.7038

Max Act: 1.4564. Min Act: -0.0001

Data Index: 472344 (C4 (Web Text))

Max Activating Token Index: 931