Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4923 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1140. Min Range: -1.1140

Max Act: 1.1140. Min Act: -0.0000

Data Index: 776620 (C4 (Web Text))

Max Activating Token Index: 979

Text #1

Max Range: 1.1140. Min Range: -1.1140

Max Act: 1.0812. Min Act: -0.0000

Data Index: 1118076 (C4 (Web Text))

Max Activating Token Index: 505

Text #2

Max Range: 1.1140. Min Range: -1.1140

Max Act: 1.0404. Min Act: -0.0000

Data Index: 671254 (C4 (Web Text))

Max Activating Token Index: 495

Text #3

Max Range: 1.1140. Min Range: -1.1140

Max Act: 1.0578. Min Act: -0.0000

Data Index: 158705 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 1.1140. Min Range: -1.1140

Max Act: 1.0138. Min Act: -0.0000

Data Index: 658459 (C4 (Web Text))

Max Activating Token Index: 967

Text #5

Max Range: 1.1140. Min Range: -1.1140

Max Act: 1.1012. Min Act: -0.0000

Data Index: 159590 (C4 (Web Text))

Max Activating Token Index: 683

Text #6

Max Range: 1.1140. Min Range: -1.1140

Max Act: 1.0628. Min Act: -0.0000

Data Index: 1319410 (C4 (Web Text))

Max Activating Token Index: 469

Text #7

Max Range: 1.1140. Min Range: -1.1140

Max Act: 0.9371. Min Act: -0.0000

Data Index: 643879 (C4 (Web Text))

Max Activating Token Index: 250

Text #8

Max Range: 1.1140. Min Range: -1.1140

Max Act: 0.9085. Min Act: -0.0000

Data Index: 703087 (C4 (Web Text))

Max Activating Token Index: 732

Text #9

Max Range: 1.1140. Min Range: -1.1140

Max Act: 0.9270. Min Act: -0.0000

Data Index: 86224 (C4 (Web Text))

Max Activating Token Index: 822

Text #10

Max Range: 1.1140. Min Range: -1.1140

Max Act: 0.9816. Min Act: -0.0000

Data Index: 1127824 (C4 (Web Text))

Max Activating Token Index: 985

Text #11

Max Range: 1.1140. Min Range: -1.1140

Max Act: 0.9163. Min Act: -0.0000

Data Index: 775869 (C4 (Web Text))

Max Activating Token Index: 220

Text #12

Max Range: 1.1140. Min Range: -1.1140

Max Act: 0.9120. Min Act: -0.0000

Data Index: 603906 (C4 (Web Text))

Max Activating Token Index: 685

Text #13

Max Range: 1.1140. Min Range: -1.1140

Max Act: 0.8815. Min Act: -0.0000

Data Index: 1290535 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 1.1140. Min Range: -1.1140

Max Act: 0.8800. Min Act: -0.0000

Data Index: 1131300 (C4 (Web Text))

Max Activating Token Index: 478

Text #15

Max Range: 1.1140. Min Range: -1.1140

Max Act: 0.9082. Min Act: -0.0000

Data Index: 498981 (C4 (Web Text))

Max Activating Token Index: 128

Text #16

Max Range: 1.1140. Min Range: -1.1140

Max Act: 0.8805. Min Act: -0.0000

Data Index: 1266485 (C4 (Web Text))

Max Activating Token Index: 988

Text #17

Max Range: 1.1140. Min Range: -1.1140

Max Act: 0.8498. Min Act: -0.0000

Data Index: 1109425 (C4 (Web Text))

Max Activating Token Index: 135

Text #18

Max Range: 1.1140. Min Range: -1.1140

Max Act: 0.8963. Min Act: -0.0000

Data Index: 1088880 (C4 (Web Text))

Max Activating Token Index: 865

Text #19

Max Range: 1.1140. Min Range: -1.1140

Max Act: 0.8696. Min Act: -0.0000

Data Index: 777346 (C4 (Web Text))

Max Activating Token Index: 745