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

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

Neuron 4779 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6130. Min Range: -1.6130

Max Act: 1.6130. Min Act: -0.0000

Data Index: 821818 (C4 (Web Text))

Max Activating Token Index: 96

Text #1

Max Range: 1.6130. Min Range: -1.6130

Max Act: 1.2712. Min Act: -0.0000

Data Index: 721935 (C4 (Web Text))

Max Activating Token Index: 230

Text #2

Max Range: 1.6130. Min Range: -1.6130

Max Act: 1.1683. Min Act: -0.0000

Data Index: 1028112 (C4 (Web Text))

Max Activating Token Index: 262

Text #3

Max Range: 1.6130. Min Range: -1.6130

Max Act: 1.0027. Min Act: -0.0000

Data Index: 495966 (C4 (Web Text))

Max Activating Token Index: 399

Text #4

Max Range: 1.6130. Min Range: -1.6130

Max Act: 1.1440. Min Act: -0.0000

Data Index: 1177748 (C4 (Web Text))

Max Activating Token Index: 504

Text #5

Max Range: 1.6130. Min Range: -1.6130

Max Act: 0.9640. Min Act: -0.0000

Data Index: 289584 (C4 (Web Text))

Max Activating Token Index: 435

Text #6

Max Range: 1.6130. Min Range: -1.6130

Max Act: 1.0959. Min Act: -0.0000

Data Index: 486066 (C4 (Web Text))

Max Activating Token Index: 928

Text #7

Max Range: 1.6130. Min Range: -1.6130

Max Act: 1.0115. Min Act: -0.0000

Data Index: 1007037 (C4 (Web Text))

Max Activating Token Index: 298

Text #8

Max Range: 1.6130. Min Range: -1.6130

Max Act: 0.9959. Min Act: -0.0000

Data Index: 350614 (C4 (Web Text))

Max Activating Token Index: 75

Text #9

Max Range: 1.6130. Min Range: -1.6130

Max Act: 1.0070. Min Act: -0.0000

Data Index: 1307918 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 1.6130. Min Range: -1.6130

Max Act: 0.9556. Min Act: -0.0000

Data Index: 334172 (C4 (Web Text))

Max Activating Token Index: 342

Text #11

Max Range: 1.6130. Min Range: -1.6130

Max Act: 0.8699. Min Act: -0.0000

Data Index: 930867 (C4 (Web Text))

Max Activating Token Index: 87

Text #12

Max Range: 1.6130. Min Range: -1.6130

Max Act: 0.8486. Min Act: -0.0000

Data Index: 1032764 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 1.6130. Min Range: -1.6130

Max Act: 0.7954. Min Act: -0.0000

Data Index: 964893 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 1.6130. Min Range: -1.6130

Max Act: 0.8200. Min Act: -0.0000

Data Index: 742861 (C4 (Web Text))

Max Activating Token Index: 944

Text #15

Max Range: 1.6130. Min Range: -1.6130

Max Act: 0.8075. Min Act: 0.0000

Data Index: 1087838 (C4 (Web Text))

Max Activating Token Index: 247

Text #16

Max Range: 1.6130. Min Range: -1.6130

Max Act: 0.8120. Min Act: -0.0000

Data Index: 992259 (C4 (Web Text))

Max Activating Token Index: 247

Text #17

Max Range: 1.6130. Min Range: -1.6130

Max Act: 0.7989. Min Act: -0.0000

Data Index: 1259034 (C4 (Web Text))

Max Activating Token Index: 972

Text #18

Max Range: 1.6130. Min Range: -1.6130

Max Act: 0.7237. Min Act: -0.0000

Data Index: 238598 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 1.6130. Min Range: -1.6130

Max Act: 0.7747. Min Act: -0.0000

Data Index: 1073973 (C4 (Web Text))

Max Activating Token Index: 613