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

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

Neuron 3748 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: 0.5237. Min Range: -0.5237

Max Act: 0.5237. Min Act: -0.0002

Data Index: 1387525 (Python Code)

Max Activating Token Index: 340

Text #1

Max Range: 0.5237. Min Range: -0.5237

Max Act: 0.4610. Min Act: -0.0002

Data Index: 98531 (C4 (Web Text))

Max Activating Token Index: 167

Text #2

Max Range: 0.5237. Min Range: -0.5237

Max Act: 0.4242. Min Act: -0.0003

Data Index: 1081765 (C4 (Web Text))

Max Activating Token Index: 289

Text #3

Max Range: 0.5237. Min Range: -0.5237

Max Act: 0.4239. Min Act: -0.0002

Data Index: 534958 (C4 (Web Text))

Max Activating Token Index: 606

Text #4

Max Range: 0.5237. Min Range: -0.5237

Max Act: 0.4177. Min Act: -0.0002

Data Index: 1583190 (Python Code)

Max Activating Token Index: 567

Text #5

Max Range: 0.5237. Min Range: -0.5237

Max Act: 0.4077. Min Act: -0.0002

Data Index: 139014 (C4 (Web Text))

Max Activating Token Index: 601

Text #6

Max Range: 0.5237. Min Range: -0.5237

Max Act: 0.4119. Min Act: -0.0002

Data Index: 109445 (C4 (Web Text))

Max Activating Token Index: 121

Text #7

Max Range: 0.5237. Min Range: -0.5237

Max Act: 0.4092. Min Act: -0.0002

Data Index: 548986 (C4 (Web Text))

Max Activating Token Index: 770

Text #8

Max Range: 0.5237. Min Range: -0.5237

Max Act: 0.3957. Min Act: -0.0002

Data Index: 1025963 (C4 (Web Text))

Max Activating Token Index: 740

Text #9

Max Range: 0.5237. Min Range: -0.5237

Max Act: 0.4009. Min Act: -0.0002

Data Index: 384182 (C4 (Web Text))

Max Activating Token Index: 131

Text #10

Max Range: 0.5237. Min Range: -0.5237

Max Act: 0.3848. Min Act: -0.0002

Data Index: 165851 (C4 (Web Text))

Max Activating Token Index: 175

Text #11

Max Range: 0.5237. Min Range: -0.5237

Max Act: 0.3928. Min Act: -0.0002

Data Index: 156532 (C4 (Web Text))

Max Activating Token Index: 279

Text #12

Max Range: 0.5237. Min Range: -0.5237

Max Act: 0.3889. Min Act: -0.0002

Data Index: 625616 (C4 (Web Text))

Max Activating Token Index: 268

Text #13

Max Range: 0.5237. Min Range: -0.5237

Max Act: 0.3871. Min Act: -0.0002

Data Index: 911190 (C4 (Web Text))

Max Activating Token Index: 240

Text #14

Max Range: 0.5237. Min Range: -0.5237

Max Act: 0.3768. Min Act: -0.0002

Data Index: 872033 (C4 (Web Text))

Max Activating Token Index: 228

Text #15

Max Range: 0.5237. Min Range: -0.5237

Max Act: 0.3739. Min Act: -0.0002

Data Index: 945182 (C4 (Web Text))

Max Activating Token Index: 437

Text #16

Max Range: 0.5237. Min Range: -0.5237

Max Act: 0.3751. Min Act: -0.0002

Data Index: 628542 (C4 (Web Text))

Max Activating Token Index: 113

Text #17

Max Range: 0.5237. Min Range: -0.5237

Max Act: 0.3871. Min Act: -0.0002

Data Index: 813738 (C4 (Web Text))

Max Activating Token Index: 198

Text #18

Max Range: 0.5237. Min Range: -0.5237

Max Act: 0.3724. Min Act: -0.0002

Data Index: 35297 (C4 (Web Text))

Max Activating Token Index: 637

Text #19

Max Range: 0.5237. Min Range: -0.5237

Max Act: 0.3771. Min Act: -0.0002

Data Index: 360824 (C4 (Web Text))

Max Activating Token Index: 348