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

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

Neuron 3507 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.5594. Min Range: -6.5594

Max Act: 6.5594. Min Act: -0.0000

Data Index: 1089056 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 6.5594. Min Range: -6.5594

Max Act: 6.1368. Min Act: -0.0000

Data Index: 29206 (C4 (Web Text))

Max Activating Token Index: 331

Text #2

Max Range: 6.5594. Min Range: -6.5594

Max Act: 5.6947. Min Act: -0.0000

Data Index: 616854 (C4 (Web Text))

Max Activating Token Index: 650

Text #3

Max Range: 6.5594. Min Range: -6.5594

Max Act: 5.6198. Min Act: -0.0000

Data Index: 528225 (C4 (Web Text))

Max Activating Token Index: 605

Text #4

Max Range: 6.5594. Min Range: -6.5594

Max Act: 5.5327. Min Act: -0.0000

Data Index: 388869 (C4 (Web Text))

Max Activating Token Index: 741

Text #5

Max Range: 6.5594. Min Range: -6.5594

Max Act: 5.3083. Min Act: -0.0000

Data Index: 48366 (C4 (Web Text))

Max Activating Token Index: 598

Text #6

Max Range: 6.5594. Min Range: -6.5594

Max Act: 4.9344. Min Act: -0.0000

Data Index: 126642 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 6.5594. Min Range: -6.5594

Max Act: 4.7196. Min Act: -0.0001

Data Index: 629613 (C4 (Web Text))

Max Activating Token Index: 934

Text #8

Max Range: 6.5594. Min Range: -6.5594

Max Act: 4.6050. Min Act: -0.0000

Data Index: 353264 (C4 (Web Text))

Max Activating Token Index: 911

Text #9

Max Range: 6.5594. Min Range: -6.5594

Max Act: 4.5352. Min Act: -0.0000

Data Index: 409500 (C4 (Web Text))

Max Activating Token Index: 777

Text #10

Max Range: 6.5594. Min Range: -6.5594

Max Act: 4.8125. Min Act: -0.0000

Data Index: 684979 (C4 (Web Text))

Max Activating Token Index: 386

Text #11

Max Range: 6.5594. Min Range: -6.5594

Max Act: 4.6919. Min Act: -0.0000

Data Index: 798151 (C4 (Web Text))

Max Activating Token Index: 189

Text #12

Max Range: 6.5594. Min Range: -6.5594

Max Act: 4.4783. Min Act: -0.0000

Data Index: 489612 (C4 (Web Text))

Max Activating Token Index: 853

Text #13

Max Range: 6.5594. Min Range: -6.5594

Max Act: 4.2353. Min Act: -0.0000

Data Index: 309849 (C4 (Web Text))

Max Activating Token Index: 965

Text #14

Max Range: 6.5594. Min Range: -6.5594

Max Act: 4.5195. Min Act: -0.0000

Data Index: 1332830 (C4 (Web Text))

Max Activating Token Index: 605

Text #15

Max Range: 6.5594. Min Range: -6.5594

Max Act: 4.1190. Min Act: -0.0000

Data Index: 1009643 (C4 (Web Text))

Max Activating Token Index: 343

Text #16

Max Range: 6.5594. Min Range: -6.5594

Max Act: 4.2489. Min Act: -0.0000

Data Index: 1163499 (C4 (Web Text))

Max Activating Token Index: 607

Text #17

Max Range: 6.5594. Min Range: -6.5594

Max Act: 4.0413. Min Act: -0.0000

Data Index: 814934 (C4 (Web Text))

Max Activating Token Index: 311

Text #18

Max Range: 6.5594. Min Range: -6.5594

Max Act: 4.1729. Min Act: -0.0000

Data Index: 1321649 (C4 (Web Text))

Max Activating Token Index: 961

Text #19

Max Range: 6.5594. Min Range: -6.5594

Max Act: 4.1845. Min Act: -0.0000

Data Index: 42891 (C4 (Web Text))

Max Activating Token Index: 34