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

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

Neuron 5962 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8789. Min Range: -1.8789

Max Act: 1.8789. Min Act: -0.0000

Data Index: 940456 (C4 (Web Text))

Max Activating Token Index: 174

Text #1

Max Range: 1.8789. Min Range: -1.8789

Max Act: 1.7989. Min Act: -0.0000

Data Index: 1417743 (Python Code)

Max Activating Token Index: 391

Text #2

Max Range: 1.8789. Min Range: -1.8789

Max Act: 1.8169. Min Act: -0.0000

Data Index: 638273 (C4 (Web Text))

Max Activating Token Index: 59

Text #3

Max Range: 1.8789. Min Range: -1.8789

Max Act: 1.8120. Min Act: -0.0000

Data Index: 1088095 (C4 (Web Text))

Max Activating Token Index: 179

Text #4

Max Range: 1.8789. Min Range: -1.8789

Max Act: 1.7614. Min Act: -0.0000

Data Index: 677288 (C4 (Web Text))

Max Activating Token Index: 109

Text #5

Max Range: 1.8789. Min Range: -1.8789

Max Act: 1.8239. Min Act: -0.0000

Data Index: 1461036 (Python Code)

Max Activating Token Index: 104

Text #6

Max Range: 1.8789. Min Range: -1.8789

Max Act: 1.6906. Min Act: -0.0000

Data Index: 599596 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 1.8789. Min Range: -1.8789

Max Act: 1.8018. Min Act: -0.0000

Data Index: 1248397 (C4 (Web Text))

Max Activating Token Index: 295

Text #8

Max Range: 1.8789. Min Range: -1.8789

Max Act: 1.6607. Min Act: -0.0000

Data Index: 1289212 (C4 (Web Text))

Max Activating Token Index: 599

Text #9

Max Range: 1.8789. Min Range: -1.8789

Max Act: 1.6102. Min Act: -0.0000

Data Index: 275140 (C4 (Web Text))

Max Activating Token Index: 36

Text #10

Max Range: 1.8789. Min Range: -1.8789

Max Act: 1.6020. Min Act: -0.0000

Data Index: 1491466 (Python Code)

Max Activating Token Index: 562

Text #11

Max Range: 1.8789. Min Range: -1.8789

Max Act: 1.6210. Min Act: -0.0000

Data Index: 107695 (C4 (Web Text))

Max Activating Token Index: 427

Text #12

Max Range: 1.8789. Min Range: -1.8789

Max Act: 1.6133. Min Act: -0.0000

Data Index: 131061 (C4 (Web Text))

Max Activating Token Index: 4

Text #13

Max Range: 1.8789. Min Range: -1.8789

Max Act: 1.7035. Min Act: -0.0000

Data Index: 568580 (C4 (Web Text))

Max Activating Token Index: 164

Text #14

Max Range: 1.8789. Min Range: -1.8789

Max Act: 1.5925. Min Act: -0.0000

Data Index: 1201226 (C4 (Web Text))

Max Activating Token Index: 583

Text #15

Max Range: 1.8789. Min Range: -1.8789

Max Act: 1.6313. Min Act: -0.0000

Data Index: 1524934 (Python Code)

Max Activating Token Index: 375

Text #16

Max Range: 1.8789. Min Range: -1.8789

Max Act: 1.5510. Min Act: -0.0000

Data Index: 545214 (C4 (Web Text))

Max Activating Token Index: 102

Text #17

Max Range: 1.8789. Min Range: -1.8789

Max Act: 1.4721. Min Act: -0.0000

Data Index: 1385238 (Python Code)

Max Activating Token Index: 818

Text #18

Max Range: 1.8789. Min Range: -1.8789

Max Act: 1.5297. Min Act: -0.0000

Data Index: 1515282 (Python Code)

Max Activating Token Index: 788

Text #19

Max Range: 1.8789. Min Range: -1.8789

Max Act: 1.5175. Min Act: -0.0000

Data Index: 1107912 (C4 (Web Text))

Max Activating Token Index: 220