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

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

Neuron 3203 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2838. Min Act: -0.0001

Data Index: 580585 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2745. Min Act: -0.0001

Data Index: 25058 (C4 (Web Text))

Max Activating Token Index: 39

Text #2

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2799. Min Act: -0.0001

Data Index: 622051 (C4 (Web Text))

Max Activating Token Index: 557

Text #3

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2902. Min Act: -0.0000

Data Index: 401421 (C4 (Web Text))

Max Activating Token Index: 962

Text #4

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2600. Min Act: -0.0000

Data Index: 409463 (C4 (Web Text))

Max Activating Token Index: 126

Text #5

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2535. Min Act: -0.0001

Data Index: 726088 (C4 (Web Text))

Max Activating Token Index: 667

Text #6

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2223. Min Act: -0.0001

Data Index: 207504 (C4 (Web Text))

Max Activating Token Index: 815

Text #7

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2473. Min Act: -0.0001

Data Index: 999852 (C4 (Web Text))

Max Activating Token Index: 646

Text #8

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2405. Min Act: -0.0001

Data Index: 1042328 (C4 (Web Text))

Max Activating Token Index: 590

Text #9

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2442. Min Act: -0.0001

Data Index: 273321 (C4 (Web Text))

Max Activating Token Index: 719

Text #10

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2307. Min Act: -0.0001

Data Index: 613142 (C4 (Web Text))

Max Activating Token Index: 500

Text #11

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2267. Min Act: -0.0000

Data Index: 655037 (C4 (Web Text))

Max Activating Token Index: 822

Text #12

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1885. Min Act: -0.0001

Data Index: 168710 (C4 (Web Text))

Max Activating Token Index: 214

Text #13

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2193. Min Act: -0.0000

Data Index: 694091 (C4 (Web Text))

Max Activating Token Index: 545

Text #14

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2015. Min Act: -0.0000

Data Index: 4504 (C4 (Web Text))

Max Activating Token Index: 199

Text #15

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2163. Min Act: -0.0000

Data Index: 1054577 (C4 (Web Text))

Max Activating Token Index: 238

Text #16

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2105. Min Act: -0.0001

Data Index: 753767 (C4 (Web Text))

Max Activating Token Index: 833

Text #17

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2103. Min Act: -0.0001

Data Index: 306363 (C4 (Web Text))

Max Activating Token Index: 733

Text #18

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2103. Min Act: -0.0000

Data Index: 57240 (C4 (Web Text))

Max Activating Token Index: 890

Text #19

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2019. Min Act: -0.0000

Data Index: 84582 (C4 (Web Text))

Max Activating Token Index: 350