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

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

Neuron 3505 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.1214. Min Range: -1.1214

Max Act: 1.1214. Min Act: -0.0002

Data Index: 215336 (C4 (Web Text))

Max Activating Token Index: 312

Text #1

Max Range: 1.1214. Min Range: -1.1214

Max Act: 1.0906. Min Act: -0.0002

Data Index: 1023685 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 1.1214. Min Range: -1.1214

Max Act: 1.0648. Min Act: -0.0002

Data Index: 1100487 (C4 (Web Text))

Max Activating Token Index: 125

Text #3

Max Range: 1.1214. Min Range: -1.1214

Max Act: 0.9902. Min Act: -0.0002

Data Index: 883290 (C4 (Web Text))

Max Activating Token Index: 737

Text #4

Max Range: 1.1214. Min Range: -1.1214

Max Act: 1.0419. Min Act: -0.0002

Data Index: 1024758 (C4 (Web Text))

Max Activating Token Index: 697

Text #5

Max Range: 1.1214. Min Range: -1.1214

Max Act: 1.0107. Min Act: -0.0002

Data Index: 402383 (C4 (Web Text))

Max Activating Token Index: 723

Text #6

Max Range: 1.1214. Min Range: -1.1214

Max Act: 0.9932. Min Act: -0.0002

Data Index: 243156 (C4 (Web Text))

Max Activating Token Index: 136

Text #7

Max Range: 1.1214. Min Range: -1.1214

Max Act: 0.9514. Min Act: -0.0002

Data Index: 941651 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 1.1214. Min Range: -1.1214

Max Act: 0.9661. Min Act: -0.0002

Data Index: 1050520 (C4 (Web Text))

Max Activating Token Index: 90

Text #9

Max Range: 1.1214. Min Range: -1.1214

Max Act: 0.9492. Min Act: -0.0002

Data Index: 743323 (C4 (Web Text))

Max Activating Token Index: 241

Text #10

Max Range: 1.1214. Min Range: -1.1214

Max Act: 0.9321. Min Act: -0.0002

Data Index: 1214452 (C4 (Web Text))

Max Activating Token Index: 76

Text #11

Max Range: 1.1214. Min Range: -1.1214

Max Act: 0.9443. Min Act: -0.0002

Data Index: 10648 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 1.1214. Min Range: -1.1214

Max Act: 0.9379. Min Act: -0.0002

Data Index: 97530 (C4 (Web Text))

Max Activating Token Index: 169

Text #13

Max Range: 1.1214. Min Range: -1.1214

Max Act: 0.9278. Min Act: -0.0002

Data Index: 14255 (C4 (Web Text))

Max Activating Token Index: 65

Text #14

Max Range: 1.1214. Min Range: -1.1214

Max Act: 0.9070. Min Act: -0.0002

Data Index: 174472 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 1.1214. Min Range: -1.1214

Max Act: 0.9177. Min Act: -0.0002

Data Index: 1031649 (C4 (Web Text))

Max Activating Token Index: 911

Text #16

Max Range: 1.1214. Min Range: -1.1214

Max Act: 0.9141. Min Act: -0.0002

Data Index: 1300568 (C4 (Web Text))

Max Activating Token Index: 95

Text #17

Max Range: 1.1214. Min Range: -1.1214

Max Act: 0.9148. Min Act: -0.0002

Data Index: 1166480 (C4 (Web Text))

Max Activating Token Index: 235

Text #18

Max Range: 1.1214. Min Range: -1.1214

Max Act: 0.8794. Min Act: -0.0002

Data Index: 588515 (C4 (Web Text))

Max Activating Token Index: 106

Text #19

Max Range: 1.1214. Min Range: -1.1214

Max Act: 0.8813. Min Act: -0.0002

Data Index: 670078 (C4 (Web Text))

Max Activating Token Index: 62