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

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

Neuron 6099 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8719. Min Range: -0.8719

Max Act: 0.8719. Min Act: -0.0000

Data Index: 1263660 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 0.8719. Min Range: -0.8719

Max Act: 0.7683. Min Act: -0.0000

Data Index: 196586 (C4 (Web Text))

Max Activating Token Index: 99

Text #2

Max Range: 0.8719. Min Range: -0.8719

Max Act: 0.7295. Min Act: -0.0000

Data Index: 438312 (C4 (Web Text))

Max Activating Token Index: 915

Text #3

Max Range: 0.8719. Min Range: -0.8719

Max Act: 0.6985. Min Act: -0.0000

Data Index: 1287920 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 0.8719. Min Range: -0.8719

Max Act: 0.7075. Min Act: -0.0000

Data Index: 527721 (C4 (Web Text))

Max Activating Token Index: 103

Text #5

Max Range: 0.8719. Min Range: -0.8719

Max Act: 0.7033. Min Act: -0.0000

Data Index: 313676 (C4 (Web Text))

Max Activating Token Index: 112

Text #6

Max Range: 0.8719. Min Range: -0.8719

Max Act: 0.6403. Min Act: -0.0000

Data Index: 80632 (C4 (Web Text))

Max Activating Token Index: 850

Text #7

Max Range: 0.8719. Min Range: -0.8719

Max Act: 0.6551. Min Act: -0.0000

Data Index: 523213 (C4 (Web Text))

Max Activating Token Index: 154

Text #8

Max Range: 0.8719. Min Range: -0.8719

Max Act: 0.6456. Min Act: -0.0000

Data Index: 357330 (C4 (Web Text))

Max Activating Token Index: 796

Text #9

Max Range: 0.8719. Min Range: -0.8719

Max Act: 0.6588. Min Act: -0.0000

Data Index: 1225331 (C4 (Web Text))

Max Activating Token Index: 128

Text #10

Max Range: 0.8719. Min Range: -0.8719

Max Act: 0.6219. Min Act: -0.0000

Data Index: 595209 (C4 (Web Text))

Max Activating Token Index: 880

Text #11

Max Range: 0.8719. Min Range: -0.8719

Max Act: 0.6500. Min Act: -0.0000

Data Index: 152591 (C4 (Web Text))

Max Activating Token Index: 328

Text #12

Max Range: 0.8719. Min Range: -0.8719

Max Act: 0.6104. Min Act: -0.0000

Data Index: 1197076 (C4 (Web Text))

Max Activating Token Index: 898

Text #13

Max Range: 0.8719. Min Range: -0.8719

Max Act: 0.6246. Min Act: -0.0000

Data Index: 851538 (C4 (Web Text))

Max Activating Token Index: 66

Text #14

Max Range: 0.8719. Min Range: -0.8719

Max Act: 0.6705. Min Act: -0.0000

Data Index: 947928 (C4 (Web Text))

Max Activating Token Index: 890

Text #15

Max Range: 0.8719. Min Range: -0.8719

Max Act: 0.6209. Min Act: -0.0000

Data Index: 1047735 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 0.8719. Min Range: -0.8719

Max Act: 0.6151. Min Act: -0.0000

Data Index: 483412 (C4 (Web Text))

Max Activating Token Index: 111

Text #17

Max Range: 0.8719. Min Range: -0.8719

Max Act: 0.6392. Min Act: -0.0000

Data Index: 1347720 (C4 (Web Text))

Max Activating Token Index: 321

Text #18

Max Range: 0.8719. Min Range: -0.8719

Max Act: 0.6708. Min Act: -0.0000

Data Index: 200113 (C4 (Web Text))

Max Activating Token Index: 1006

Text #19

Max Range: 0.8719. Min Range: -0.8719

Max Act: 0.6145. Min Act: -0.0000

Data Index: 1106154 (C4 (Web Text))

Max Activating Token Index: 4