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

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

Neuron 1538 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8993. Min Range: -1.8993

Max Act: 1.8993. Min Act: -0.0000

Data Index: 458498 (C4 (Web Text))

Max Activating Token Index: 535

Text #1

Max Range: 1.8993. Min Range: -1.8993

Max Act: 1.7151. Min Act: -0.0000

Data Index: 411473 (C4 (Web Text))

Max Activating Token Index: 595

Text #2

Max Range: 1.8993. Min Range: -1.8993

Max Act: 1.6906. Min Act: -0.0000

Data Index: 1049119 (C4 (Web Text))

Max Activating Token Index: 389

Text #3

Max Range: 1.8993. Min Range: -1.8993

Max Act: 1.6740. Min Act: -0.0000

Data Index: 719368 (C4 (Web Text))

Max Activating Token Index: 464

Text #4

Max Range: 1.8993. Min Range: -1.8993

Max Act: 1.5176. Min Act: -0.0000

Data Index: 942995 (C4 (Web Text))

Max Activating Token Index: 727

Text #5

Max Range: 1.8993. Min Range: -1.8993

Max Act: 1.4313. Min Act: -0.0000

Data Index: 1147774 (C4 (Web Text))

Max Activating Token Index: 76

Text #6

Max Range: 1.8993. Min Range: -1.8993

Max Act: 1.2791. Min Act: -0.0000

Data Index: 1124319 (C4 (Web Text))

Max Activating Token Index: 761

Text #7

Max Range: 1.8993. Min Range: -1.8993

Max Act: 1.1439. Min Act: -0.0000

Data Index: 49228 (C4 (Web Text))

Max Activating Token Index: 362

Text #8

Max Range: 1.8993. Min Range: -1.8993

Max Act: 1.1447. Min Act: -0.0000

Data Index: 833283 (C4 (Web Text))

Max Activating Token Index: 552

Text #9

Max Range: 1.8993. Min Range: -1.8993

Max Act: 1.0282. Min Act: -0.0000

Data Index: 989702 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 1.8993. Min Range: -1.8993

Max Act: 0.9888. Min Act: -0.0000

Data Index: 1323977 (C4 (Web Text))

Max Activating Token Index: 916

Text #11

Max Range: 1.8993. Min Range: -1.8993

Max Act: 0.9319. Min Act: -0.0000

Data Index: 798462 (C4 (Web Text))

Max Activating Token Index: 926

Text #12

Max Range: 1.8993. Min Range: -1.8993

Max Act: 0.9435. Min Act: -0.0000

Data Index: 80580 (C4 (Web Text))

Max Activating Token Index: 157

Text #13

Max Range: 1.8993. Min Range: -1.8993

Max Act: 0.8873. Min Act: -0.0000

Data Index: 809573 (C4 (Web Text))

Max Activating Token Index: 228

Text #14

Max Range: 1.8993. Min Range: -1.8993

Max Act: 0.9228. Min Act: -0.0000

Data Index: 470773 (C4 (Web Text))

Max Activating Token Index: 499

Text #15

Max Range: 1.8993. Min Range: -1.8993

Max Act: 0.9187. Min Act: -0.0000

Data Index: 680582 (C4 (Web Text))

Max Activating Token Index: 899

Text #16

Max Range: 1.8993. Min Range: -1.8993

Max Act: 0.8960. Min Act: -0.0000

Data Index: 1097850 (C4 (Web Text))

Max Activating Token Index: 418

Text #17

Max Range: 1.8993. Min Range: -1.8993

Max Act: 0.8647. Min Act: -0.0000

Data Index: 771112 (C4 (Web Text))

Max Activating Token Index: 467

Text #18

Max Range: 1.8993. Min Range: -1.8993

Max Act: 0.8704. Min Act: -0.0000

Data Index: 467863 (C4 (Web Text))

Max Activating Token Index: 833

Text #19

Max Range: 1.8993. Min Range: -1.8993

Max Act: 0.8926. Min Act: -0.0000

Data Index: 1060101 (C4 (Web Text))

Max Activating Token Index: 551