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

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

Neuron 5732 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.8016. Min Act: -0.0000

Data Index: 1246621 (C4 (Web Text))

Max Activating Token Index: 897

Text #1

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.7983. Min Act: -0.0000

Data Index: 353905 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.7796. Min Act: -0.0000

Data Index: 195357 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.7475. Min Act: -0.0000

Data Index: 879813 (C4 (Web Text))

Max Activating Token Index: 663

Text #4

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.7179. Min Act: -0.0000

Data Index: 419857 (C4 (Web Text))

Max Activating Token Index: 76

Text #5

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.7548. Min Act: -0.0000

Data Index: 1129547 (C4 (Web Text))

Max Activating Token Index: 590

Text #6

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.6624. Min Act: -0.0000

Data Index: 158562 (C4 (Web Text))

Max Activating Token Index: 61

Text #7

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.6402. Min Act: -0.0000

Data Index: 337011 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.6815. Min Act: -0.0000

Data Index: 896630 (C4 (Web Text))

Max Activating Token Index: 483

Text #9

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.6923. Min Act: -0.0000

Data Index: 907942 (C4 (Web Text))

Max Activating Token Index: 798

Text #10

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.6911. Min Act: -0.0000

Data Index: 967964 (C4 (Web Text))

Max Activating Token Index: 265

Text #11

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.6762. Min Act: -0.0000

Data Index: 751390 (C4 (Web Text))

Max Activating Token Index: 697

Text #12

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.6703. Min Act: -0.0000

Data Index: 1207553 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.6593. Min Act: -0.0000

Data Index: 1164622 (C4 (Web Text))

Max Activating Token Index: 44

Text #14

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.6338. Min Act: -0.0000

Data Index: 405356 (C4 (Web Text))

Max Activating Token Index: 190

Text #15

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.6463. Min Act: -0.0000

Data Index: 744316 (C4 (Web Text))

Max Activating Token Index: 829

Text #16

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.6245. Min Act: -0.0000

Data Index: 1353680 (C4 (Web Text))

Max Activating Token Index: 43

Text #17

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.6401. Min Act: -0.0000

Data Index: 151052 (C4 (Web Text))

Max Activating Token Index: 241

Text #18

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.5787. Min Act: -0.0000

Data Index: 901422 (C4 (Web Text))

Max Activating Token Index: 154

Text #19

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.6076. Min Act: -0.0000

Data Index: 1000303 (C4 (Web Text))

Max Activating Token Index: 602