Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 452 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0393. Min Act: -0.0003

Data Index: 1023705 (C4 (Web Text))

Max Activating Token Index: 92

Text #1

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0312. Min Act: -0.0003

Data Index: 222734 (C4 (Web Text))

Max Activating Token Index: 52

Text #2

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0288. Min Act: -0.0003

Data Index: 574296 (C4 (Web Text))

Max Activating Token Index: 577

Text #3

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0261. Min Act: -0.0002

Data Index: 652669 (C4 (Web Text))

Max Activating Token Index: 681

Text #4

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0258. Min Act: -0.0002

Data Index: 1301864 (C4 (Web Text))

Max Activating Token Index: 116

Text #5

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0250. Min Act: -0.0002

Data Index: 523304 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0254. Min Act: -0.0002

Data Index: 651234 (C4 (Web Text))

Max Activating Token Index: 542

Text #7

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0252. Min Act: -0.0002

Data Index: 784336 (C4 (Web Text))

Max Activating Token Index: 899

Text #8

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0248. Min Act: -0.0003

Data Index: 867994 (C4 (Web Text))

Max Activating Token Index: 744

Text #9

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0247. Min Act: -0.0003

Data Index: 557432 (C4 (Web Text))

Max Activating Token Index: 626

Text #10

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0258. Min Act: -0.0003

Data Index: 687558 (C4 (Web Text))

Max Activating Token Index: 900

Text #11

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0243. Min Act: -0.0003

Data Index: 822438 (C4 (Web Text))

Max Activating Token Index: 15

Text #12

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0233. Min Act: -0.0003

Data Index: 843617 (C4 (Web Text))

Max Activating Token Index: 729

Text #13

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0242. Min Act: -0.0002

Data Index: 206932 (C4 (Web Text))

Max Activating Token Index: 981

Text #14

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0242. Min Act: -0.0003

Data Index: 235061 (C4 (Web Text))

Max Activating Token Index: 737

Text #15

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0240. Min Act: -0.0003

Data Index: 1231679 (C4 (Web Text))

Max Activating Token Index: 888

Text #16

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0234. Min Act: -0.0003

Data Index: 1215011 (C4 (Web Text))

Max Activating Token Index: 965

Text #17

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0239. Min Act: -0.0003

Data Index: 189668 (C4 (Web Text))

Max Activating Token Index: 493

Text #18

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0233. Min Act: -0.0003

Data Index: 695880 (C4 (Web Text))

Max Activating Token Index: 510

Text #19

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0233. Min Act: -0.0003

Data Index: 313125 (C4 (Web Text))

Max Activating Token Index: 775