Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1911 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.3626. Min Range: -1.3626

Max Act: 1.3293. Min Act: -0.0003

Data Index: 379860 (C4 (Web Text))

Max Activating Token Index: 853

Text #1

Max Range: 1.3626. Min Range: -1.3626

Max Act: 1.3626. Min Act: -0.0003

Data Index: 828691 (C4 (Web Text))

Max Activating Token Index: 339

Text #2

Max Range: 1.3626. Min Range: -1.3626

Max Act: 1.3138. Min Act: -0.0003

Data Index: 1203437 (C4 (Web Text))

Max Activating Token Index: 948

Text #3

Max Range: 1.3626. Min Range: -1.3626

Max Act: 1.2916. Min Act: -0.0003

Data Index: 953378 (C4 (Web Text))

Max Activating Token Index: 697

Text #4

Max Range: 1.3626. Min Range: -1.3626

Max Act: 1.2859. Min Act: -0.0003

Data Index: 325956 (C4 (Web Text))

Max Activating Token Index: 500

Text #5

Max Range: 1.3626. Min Range: -1.3626

Max Act: 1.2327. Min Act: -0.0003

Data Index: 125106 (C4 (Web Text))

Max Activating Token Index: 228

Text #6

Max Range: 1.3626. Min Range: -1.3626

Max Act: 1.2937. Min Act: -0.0003

Data Index: 432427 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 1.3626. Min Range: -1.3626

Max Act: 1.3090. Min Act: -0.0003

Data Index: 1290485 (C4 (Web Text))

Max Activating Token Index: 1014

Text #8

Max Range: 1.3626. Min Range: -1.3626

Max Act: 1.2579. Min Act: -0.0003

Data Index: 571216 (C4 (Web Text))

Max Activating Token Index: 863

Text #9

Max Range: 1.3626. Min Range: -1.3626

Max Act: 1.1331. Min Act: -0.0003

Data Index: 1014402 (C4 (Web Text))

Max Activating Token Index: 215

Text #10

Max Range: 1.3626. Min Range: -1.3626

Max Act: 1.0950. Min Act: -0.0003

Data Index: 525574 (C4 (Web Text))

Max Activating Token Index: 643

Text #11

Max Range: 1.3626. Min Range: -1.3626

Max Act: 1.1361. Min Act: -0.0003

Data Index: 458253 (C4 (Web Text))

Max Activating Token Index: 864

Text #12

Max Range: 1.3626. Min Range: -1.3626

Max Act: 1.1826. Min Act: -0.0003

Data Index: 1174894 (C4 (Web Text))

Max Activating Token Index: 106

Text #13

Max Range: 1.3626. Min Range: -1.3626

Max Act: 1.2171. Min Act: -0.0003

Data Index: 706437 (C4 (Web Text))

Max Activating Token Index: 602

Text #14

Max Range: 1.3626. Min Range: -1.3626

Max Act: 1.1123. Min Act: -0.0003

Data Index: 722278 (C4 (Web Text))

Max Activating Token Index: 605

Text #15

Max Range: 1.3626. Min Range: -1.3626

Max Act: 1.2025. Min Act: -0.0003

Data Index: 779726 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 1.3626. Min Range: -1.3626

Max Act: 1.1633. Min Act: -0.0003

Data Index: 852303 (C4 (Web Text))

Max Activating Token Index: 892

Text #17

Max Range: 1.3626. Min Range: -1.3626

Max Act: 1.1896. Min Act: -0.0003

Data Index: 635562 (C4 (Web Text))

Max Activating Token Index: 618

Text #18

Max Range: 1.3626. Min Range: -1.3626

Max Act: 1.0895. Min Act: -0.0003

Data Index: 1284788 (C4 (Web Text))

Max Activating Token Index: 165

Text #19

Max Range: 1.3626. Min Range: -1.3626

Max Act: 1.1879. Min Act: -0.0003

Data Index: 394810 (C4 (Web Text))

Max Activating Token Index: 181