Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3569 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2562. Min Range: -0.2562

Max Act: 0.2562. Min Act: -0.0001

Data Index: 822799 (C4 (Web Text))

Max Activating Token Index: 909

Text #1

Max Range: 0.2562. Min Range: -0.2562

Max Act: 0.2389. Min Act: -0.0002

Data Index: 636538 (C4 (Web Text))

Max Activating Token Index: 796

Text #2

Max Range: 0.2562. Min Range: -0.2562

Max Act: 0.2295. Min Act: -0.0001

Data Index: 1055207 (C4 (Web Text))

Max Activating Token Index: 593

Text #3

Max Range: 0.2562. Min Range: -0.2562

Max Act: 0.2353. Min Act: -0.0001

Data Index: 1233804 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 0.2562. Min Range: -0.2562

Max Act: 0.2203. Min Act: -0.0002

Data Index: 327560 (C4 (Web Text))

Max Activating Token Index: 820

Text #5

Max Range: 0.2562. Min Range: -0.2562

Max Act: 0.2354. Min Act: -0.0001

Data Index: 252989 (C4 (Web Text))

Max Activating Token Index: 202

Text #6

Max Range: 0.2562. Min Range: -0.2562

Max Act: 0.2326. Min Act: -0.0002

Data Index: 189650 (C4 (Web Text))

Max Activating Token Index: 545

Text #7

Max Range: 0.2562. Min Range: -0.2562

Max Act: 0.2332. Min Act: -0.0002

Data Index: 284874 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 0.2562. Min Range: -0.2562

Max Act: 0.2306. Min Act: -0.0001

Data Index: 759260 (C4 (Web Text))

Max Activating Token Index: 846

Text #9

Max Range: 0.2562. Min Range: -0.2562

Max Act: 0.2156. Min Act: -0.0002

Data Index: 602621 (C4 (Web Text))

Max Activating Token Index: 608

Text #10

Max Range: 0.2562. Min Range: -0.2562

Max Act: 0.2228. Min Act: -0.0002

Data Index: 104694 (C4 (Web Text))

Max Activating Token Index: 43

Text #11

Max Range: 0.2562. Min Range: -0.2562

Max Act: 0.2218. Min Act: -0.0002

Data Index: 654612 (C4 (Web Text))

Max Activating Token Index: 46

Text #12

Max Range: 0.2562. Min Range: -0.2562

Max Act: 0.2207. Min Act: -0.0002

Data Index: 232595 (C4 (Web Text))

Max Activating Token Index: 5

Text #13

Max Range: 0.2562. Min Range: -0.2562

Max Act: 0.2214. Min Act: -0.0002

Data Index: 818364 (C4 (Web Text))

Max Activating Token Index: 131

Text #14

Max Range: 0.2562. Min Range: -0.2562

Max Act: 0.2277. Min Act: -0.0001

Data Index: 917557 (C4 (Web Text))

Max Activating Token Index: 879

Text #15

Max Range: 0.2562. Min Range: -0.2562

Max Act: 0.2276. Min Act: -0.0001

Data Index: 1203850 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 0.2562. Min Range: -0.2562

Max Act: 0.2118. Min Act: -0.0001

Data Index: 318685 (C4 (Web Text))

Max Activating Token Index: 80

Text #17

Max Range: 0.2562. Min Range: -0.2562

Max Act: 0.2120. Min Act: -0.0002

Data Index: 343611 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 0.2562. Min Range: -0.2562

Max Act: 0.2095. Min Act: -0.0002

Data Index: 26828 (C4 (Web Text))

Max Activating Token Index: 720

Text #19

Max Range: 0.2562. Min Range: -0.2562

Max Act: 0.2105. Min Act: -0.0002

Data Index: 531549 (C4 (Web Text))

Max Activating Token Index: 31