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

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

Neuron 3072 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7041. Min Range: -1.7041

Max Act: 1.5954. Min Act: -0.0000

Data Index: 608106 (C4 (Web Text))

Max Activating Token Index: 866

Text #1

Max Range: 1.7041. Min Range: -1.7041

Max Act: 1.6711. Min Act: -0.0000

Data Index: 1062778 (C4 (Web Text))

Max Activating Token Index: 547

Text #2

Max Range: 1.7041. Min Range: -1.7041

Max Act: 1.7041. Min Act: -0.0000

Data Index: 890816 (C4 (Web Text))

Max Activating Token Index: 121

Text #3

Max Range: 1.7041. Min Range: -1.7041

Max Act: 1.5440. Min Act: -0.0000

Data Index: 702261 (C4 (Web Text))

Max Activating Token Index: 537

Text #4

Max Range: 1.7041. Min Range: -1.7041

Max Act: 1.6337. Min Act: -0.0000

Data Index: 1321489 (C4 (Web Text))

Max Activating Token Index: 494

Text #5

Max Range: 1.7041. Min Range: -1.7041

Max Act: 1.5399. Min Act: -0.0000

Data Index: 1218323 (C4 (Web Text))

Max Activating Token Index: 817

Text #6

Max Range: 1.7041. Min Range: -1.7041

Max Act: 1.6216. Min Act: -0.0000

Data Index: 1222077 (C4 (Web Text))

Max Activating Token Index: 541

Text #7

Max Range: 1.7041. Min Range: -1.7041

Max Act: 1.5065. Min Act: -0.0000

Data Index: 46007 (C4 (Web Text))

Max Activating Token Index: 636

Text #8

Max Range: 1.7041. Min Range: -1.7041

Max Act: 1.5752. Min Act: -0.0000

Data Index: 1223387 (C4 (Web Text))

Max Activating Token Index: 179

Text #9

Max Range: 1.7041. Min Range: -1.7041

Max Act: 1.5757. Min Act: -0.0000

Data Index: 1181039 (C4 (Web Text))

Max Activating Token Index: 646

Text #10

Max Range: 1.7041. Min Range: -1.7041

Max Act: 1.6312. Min Act: -0.0000

Data Index: 769466 (C4 (Web Text))

Max Activating Token Index: 1005

Text #11

Max Range: 1.7041. Min Range: -1.7041

Max Act: 1.5436. Min Act: -0.0000

Data Index: 1143834 (C4 (Web Text))

Max Activating Token Index: 361

Text #12

Max Range: 1.7041. Min Range: -1.7041

Max Act: 1.5199. Min Act: -0.0000

Data Index: 1300942 (C4 (Web Text))

Max Activating Token Index: 704

Text #13

Max Range: 1.7041. Min Range: -1.7041

Max Act: 1.4330. Min Act: -0.0000

Data Index: 545820 (C4 (Web Text))

Max Activating Token Index: 636

Text #14

Max Range: 1.7041. Min Range: -1.7041

Max Act: 1.5224. Min Act: -0.0000

Data Index: 40912 (C4 (Web Text))

Max Activating Token Index: 107

Text #15

Max Range: 1.7041. Min Range: -1.7041

Max Act: 1.5181. Min Act: -0.0000

Data Index: 491203 (C4 (Web Text))

Max Activating Token Index: 795

Text #16

Max Range: 1.7041. Min Range: -1.7041

Max Act: 1.4838. Min Act: -0.0000

Data Index: 47322 (C4 (Web Text))

Max Activating Token Index: 961

Text #17

Max Range: 1.7041. Min Range: -1.7041

Max Act: 1.4800. Min Act: -0.0000

Data Index: 667995 (C4 (Web Text))

Max Activating Token Index: 496

Text #18

Max Range: 1.7041. Min Range: -1.7041

Max Act: 1.4748. Min Act: -0.0000

Data Index: 554284 (C4 (Web Text))

Max Activating Token Index: 954

Text #19

Max Range: 1.7041. Min Range: -1.7041

Max Act: 1.4706. Min Act: -0.0000

Data Index: 745486 (C4 (Web Text))

Max Activating Token Index: 913