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

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

Neuron 2858 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: 1.1626. Min Range: -1.1626

Max Act: 1.1626. Min Act: -0.0001

Data Index: 1644781 (Python Code)

Max Activating Token Index: 799

Text #1

Max Range: 1.1626. Min Range: -1.1626

Max Act: 1.0086. Min Act: -0.0001

Data Index: 1620912 (Python Code)

Max Activating Token Index: 269

Text #2

Max Range: 1.1626. Min Range: -1.1626

Max Act: 1.0122. Min Act: -0.0001

Data Index: 1590227 (Python Code)

Max Activating Token Index: 94

Text #3

Max Range: 1.1626. Min Range: -1.1626

Max Act: 0.9604. Min Act: -0.0001

Data Index: 1554860 (Python Code)

Max Activating Token Index: 208

Text #4

Max Range: 1.1626. Min Range: -1.1626

Max Act: 1.0240. Min Act: -0.0001

Data Index: 1535858 (Python Code)

Max Activating Token Index: 323

Text #5

Max Range: 1.1626. Min Range: -1.1626

Max Act: 0.9810. Min Act: -0.0001

Data Index: 1591713 (Python Code)

Max Activating Token Index: 484

Text #6

Max Range: 1.1626. Min Range: -1.1626

Max Act: 0.9506. Min Act: -0.0001

Data Index: 1441430 (Python Code)

Max Activating Token Index: 35

Text #7

Max Range: 1.1626. Min Range: -1.1626

Max Act: 0.9912. Min Act: -0.0001

Data Index: 269842 (C4 (Web Text))

Max Activating Token Index: 945

Text #8

Max Range: 1.1626. Min Range: -1.1626

Max Act: 0.9328. Min Act: -0.0001

Data Index: 1379868 (Python Code)

Max Activating Token Index: 49

Text #9

Max Range: 1.1626. Min Range: -1.1626

Max Act: 0.9392. Min Act: -0.0001

Data Index: 1456088 (Python Code)

Max Activating Token Index: 917

Text #10

Max Range: 1.1626. Min Range: -1.1626

Max Act: 0.9683. Min Act: -0.0001

Data Index: 1593387 (Python Code)

Max Activating Token Index: 182

Text #11

Max Range: 1.1626. Min Range: -1.1626

Max Act: 0.9502. Min Act: -0.0001

Data Index: 1551496 (Python Code)

Max Activating Token Index: 321

Text #12

Max Range: 1.1626. Min Range: -1.1626

Max Act: 0.9821. Min Act: -0.0001

Data Index: 1600018 (Python Code)

Max Activating Token Index: 996

Text #13

Max Range: 1.1626. Min Range: -1.1626

Max Act: 0.9576. Min Act: -0.0001

Data Index: 1367128 (Python Code)

Max Activating Token Index: 86

Text #14

Max Range: 1.1626. Min Range: -1.1626

Max Act: 0.9183. Min Act: -0.0001

Data Index: 1093269 (C4 (Web Text))

Max Activating Token Index: 718

Text #15

Max Range: 1.1626. Min Range: -1.1626

Max Act: 0.9069. Min Act: -0.0001

Data Index: 889220 (C4 (Web Text))

Max Activating Token Index: 307

Text #16

Max Range: 1.1626. Min Range: -1.1626

Max Act: 0.8994. Min Act: -0.0001

Data Index: 1381163 (Python Code)

Max Activating Token Index: 357

Text #17

Max Range: 1.1626. Min Range: -1.1626

Max Act: 0.9076. Min Act: -0.0001

Data Index: 1530163 (Python Code)

Max Activating Token Index: 765

Text #18

Max Range: 1.1626. Min Range: -1.1626

Max Act: 0.9503. Min Act: -0.0001

Data Index: 607689 (C4 (Web Text))

Max Activating Token Index: 229

Text #19

Max Range: 1.1626. Min Range: -1.1626

Max Act: 0.9759. Min Act: -0.0001

Data Index: 1396544 (Python Code)

Max Activating Token Index: 736