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

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

Neuron 3542 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.9829. Min Act: -0.0000

Data Index: 124988 (C4 (Web Text))

Max Activating Token Index: 713

Text #1

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.9799. Min Act: -0.0000

Data Index: 900839 (C4 (Web Text))

Max Activating Token Index: 352

Text #2

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.7669. Min Act: 0.0003

Data Index: 1323044 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.7751. Min Act: -0.0000

Data Index: 945403 (C4 (Web Text))

Max Activating Token Index: 875

Text #4

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.7802. Min Act: -0.0000

Data Index: 1148656 (C4 (Web Text))

Max Activating Token Index: 105

Text #5

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.7486. Min Act: 0.0003

Data Index: 213778 (C4 (Web Text))

Max Activating Token Index: 480

Text #6

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.7078. Min Act: -0.0000

Data Index: 1238119 (C4 (Web Text))

Max Activating Token Index: 123

Text #7

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.7290. Min Act: -0.0000

Data Index: 54593 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.7052. Min Act: -0.0000

Data Index: 588120 (C4 (Web Text))

Max Activating Token Index: 983

Text #9

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.7201. Min Act: 0.0000

Data Index: 512513 (C4 (Web Text))

Max Activating Token Index: 397

Text #10

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.7172. Min Act: 0.0003

Data Index: 511946 (C4 (Web Text))

Max Activating Token Index: 737

Text #11

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.7035. Min Act: -0.0000

Data Index: 1089288 (C4 (Web Text))

Max Activating Token Index: 365

Text #12

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.6847. Min Act: 0.0000

Data Index: 864973 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.6810. Min Act: -0.0000

Data Index: 1064439 (C4 (Web Text))

Max Activating Token Index: 284

Text #14

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.6542. Min Act: -0.0000

Data Index: 753591 (C4 (Web Text))

Max Activating Token Index: 852

Text #15

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.6558. Min Act: 0.0000

Data Index: 41965 (C4 (Web Text))

Max Activating Token Index: 332

Text #16

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.6702. Min Act: -0.0000

Data Index: 427678 (C4 (Web Text))

Max Activating Token Index: 88

Text #17

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.6588. Min Act: -0.0000

Data Index: 602774 (C4 (Web Text))

Max Activating Token Index: 22

Text #18

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.6691. Min Act: -0.0000

Data Index: 711506 (C4 (Web Text))

Max Activating Token Index: 834

Text #19

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.6278. Min Act: 0.0001

Data Index: 634329 (C4 (Web Text))

Max Activating Token Index: 264