Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3951 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1065. Min Range: -1.1065

Max Act: 1.0164. Min Act: -0.0000

Data Index: 1190769 (C4 (Web Text))

Max Activating Token Index: 281

Text #1

Max Range: 1.1065. Min Range: -1.1065

Max Act: 1.1065. Min Act: -0.0000

Data Index: 1090547 (C4 (Web Text))

Max Activating Token Index: 718

Text #2

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.9843. Min Act: -0.0000

Data Index: 1651743 (Python Code)

Max Activating Token Index: 694

Text #3

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.9051. Min Act: -0.0000

Data Index: 1259214 (C4 (Web Text))

Max Activating Token Index: 131

Text #4

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.8912. Min Act: -0.0000

Data Index: 1426760 (Python Code)

Max Activating Token Index: 945

Text #5

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.9935. Min Act: -0.0000

Data Index: 1314074 (C4 (Web Text))

Max Activating Token Index: 315

Text #6

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.8725. Min Act: -0.0000

Data Index: 204783 (C4 (Web Text))

Max Activating Token Index: 378

Text #7

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.9152. Min Act: -0.0000

Data Index: 382069 (C4 (Web Text))

Max Activating Token Index: 228

Text #8

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.8825. Min Act: -0.0000

Data Index: 1388494 (Python Code)

Max Activating Token Index: 616

Text #9

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.8745. Min Act: -0.0000

Data Index: 1446339 (Python Code)

Max Activating Token Index: 670

Text #10

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.8575. Min Act: -0.0000

Data Index: 924121 (C4 (Web Text))

Max Activating Token Index: 506

Text #11

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.8312. Min Act: -0.0000

Data Index: 235498 (C4 (Web Text))

Max Activating Token Index: 61

Text #12

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.8542. Min Act: -0.0000

Data Index: 91503 (C4 (Web Text))

Max Activating Token Index: 611

Text #13

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.8215. Min Act: -0.0000

Data Index: 910612 (C4 (Web Text))

Max Activating Token Index: 956

Text #14

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.8158. Min Act: -0.0000

Data Index: 613696 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.8542. Min Act: -0.0000

Data Index: 1185696 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.7966. Min Act: -0.0000

Data Index: 1442868 (Python Code)

Max Activating Token Index: 80

Text #17

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.7548. Min Act: -0.0000

Data Index: 1361114 (Python Code)

Max Activating Token Index: 308

Text #18

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.7965. Min Act: -0.0000

Data Index: 531591 (C4 (Web Text))

Max Activating Token Index: 203

Text #19

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.8191. Min Act: -0.0000

Data Index: 109868 (C4 (Web Text))

Max Activating Token Index: 173