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

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

Neuron 2479 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7513. Min Range: -0.7513

Max Act: 0.7513. Min Act: -0.0001

Data Index: 462926 (C4 (Web Text))

Max Activating Token Index: 781

Text #1

Max Range: 0.7513. Min Range: -0.7513

Max Act: 0.6849. Min Act: -0.0001

Data Index: 652138 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 0.7513. Min Range: -0.7513

Max Act: 0.6670. Min Act: -0.0001

Data Index: 925592 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 0.7513. Min Range: -0.7513

Max Act: 0.6519. Min Act: -0.0001

Data Index: 1153873 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 0.7513. Min Range: -0.7513

Max Act: 0.6520. Min Act: -0.0001

Data Index: 616574 (C4 (Web Text))

Max Activating Token Index: 590

Text #5

Max Range: 0.7513. Min Range: -0.7513

Max Act: 0.6432. Min Act: -0.0001

Data Index: 914208 (C4 (Web Text))

Max Activating Token Index: 249

Text #6

Max Range: 0.7513. Min Range: -0.7513

Max Act: 0.5895. Min Act: -0.0001

Data Index: 345398 (C4 (Web Text))

Max Activating Token Index: 926

Text #7

Max Range: 0.7513. Min Range: -0.7513

Max Act: 0.6092. Min Act: -0.0001

Data Index: 871061 (C4 (Web Text))

Max Activating Token Index: 22

Text #8

Max Range: 0.7513. Min Range: -0.7513

Max Act: 0.5848. Min Act: -0.0001

Data Index: 589724 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 0.7513. Min Range: -0.7513

Max Act: 0.6228. Min Act: -0.0001

Data Index: 1005141 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 0.7513. Min Range: -0.7513

Max Act: 0.6653. Min Act: -0.0001

Data Index: 1237652 (C4 (Web Text))

Max Activating Token Index: 258

Text #11

Max Range: 0.7513. Min Range: -0.7513

Max Act: 0.5945. Min Act: -0.0001

Data Index: 147277 (C4 (Web Text))

Max Activating Token Index: 13

Text #12

Max Range: 0.7513. Min Range: -0.7513

Max Act: 0.6334. Min Act: -0.0001

Data Index: 714505 (C4 (Web Text))

Max Activating Token Index: 35

Text #13

Max Range: 0.7513. Min Range: -0.7513

Max Act: 0.5707. Min Act: -0.0001

Data Index: 24936 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 0.7513. Min Range: -0.7513

Max Act: 0.5507. Min Act: -0.0001

Data Index: 206676 (C4 (Web Text))

Max Activating Token Index: 281

Text #15

Max Range: 0.7513. Min Range: -0.7513

Max Act: 0.5824. Min Act: -0.0001

Data Index: 802174 (C4 (Web Text))

Max Activating Token Index: 51

Text #16

Max Range: 0.7513. Min Range: -0.7513

Max Act: 0.5624. Min Act: -0.0001

Data Index: 955436 (C4 (Web Text))

Max Activating Token Index: 121

Text #17

Max Range: 0.7513. Min Range: -0.7513

Max Act: 0.6186. Min Act: -0.0001

Data Index: 620228 (C4 (Web Text))

Max Activating Token Index: 364

Text #18

Max Range: 0.7513. Min Range: -0.7513

Max Act: 0.5866. Min Act: -0.0001

Data Index: 9891 (C4 (Web Text))

Max Activating Token Index: 17

Text #19

Max Range: 0.7513. Min Range: -0.7513

Max Act: 0.5631. Min Act: -0.0001

Data Index: 595814 (C4 (Web Text))

Max Activating Token Index: 48