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

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

Neuron 1231 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: 3.7744. Min Range: -3.7744

Max Act: 3.7744. Min Act: -0.0000

Data Index: 692848 (C4 (Web Text))

Max Activating Token Index: 452

Text #1

Max Range: 3.7744. Min Range: -3.7744

Max Act: 3.3619. Min Act: -0.0000

Data Index: 614229 (C4 (Web Text))

Max Activating Token Index: 442

Text #2

Max Range: 3.7744. Min Range: -3.7744

Max Act: 3.0421. Min Act: -0.0000

Data Index: 304130 (C4 (Web Text))

Max Activating Token Index: 904

Text #3

Max Range: 3.7744. Min Range: -3.7744

Max Act: 2.8830. Min Act: -0.0000

Data Index: 323235 (C4 (Web Text))

Max Activating Token Index: 33

Text #4

Max Range: 3.7744. Min Range: -3.7744

Max Act: 2.8862. Min Act: -0.0000

Data Index: 917081 (C4 (Web Text))

Max Activating Token Index: 289

Text #5

Max Range: 3.7744. Min Range: -3.7744

Max Act: 2.8369. Min Act: -0.0000

Data Index: 635019 (C4 (Web Text))

Max Activating Token Index: 107

Text #6

Max Range: 3.7744. Min Range: -3.7744

Max Act: 2.8017. Min Act: -0.0000

Data Index: 1316180 (C4 (Web Text))

Max Activating Token Index: 614

Text #7

Max Range: 3.7744. Min Range: -3.7744

Max Act: 2.6950. Min Act: -0.0000

Data Index: 1094102 (C4 (Web Text))

Max Activating Token Index: 744

Text #8

Max Range: 3.7744. Min Range: -3.7744

Max Act: 2.6751. Min Act: -0.0000

Data Index: 1067142 (C4 (Web Text))

Max Activating Token Index: 964

Text #9

Max Range: 3.7744. Min Range: -3.7744

Max Act: 2.6851. Min Act: -0.0000

Data Index: 1211216 (C4 (Web Text))

Max Activating Token Index: 899

Text #10

Max Range: 3.7744. Min Range: -3.7744

Max Act: 2.6367. Min Act: -0.0000

Data Index: 499428 (C4 (Web Text))

Max Activating Token Index: 47

Text #11

Max Range: 3.7744. Min Range: -3.7744

Max Act: 2.6212. Min Act: -0.0000

Data Index: 735720 (C4 (Web Text))

Max Activating Token Index: 114

Text #12

Max Range: 3.7744. Min Range: -3.7744

Max Act: 2.7248. Min Act: -0.0000

Data Index: 1249057 (C4 (Web Text))

Max Activating Token Index: 266

Text #13

Max Range: 3.7744. Min Range: -3.7744

Max Act: 2.2110. Min Act: -0.0000

Data Index: 783400 (C4 (Web Text))

Max Activating Token Index: 747

Text #14

Max Range: 3.7744. Min Range: -3.7744

Max Act: 2.5787. Min Act: -0.0000

Data Index: 549215 (C4 (Web Text))

Max Activating Token Index: 111

Text #15

Max Range: 3.7744. Min Range: -3.7744

Max Act: 2.5738. Min Act: -0.0000

Data Index: 95301 (C4 (Web Text))

Max Activating Token Index: 238

Text #16

Max Range: 3.7744. Min Range: -3.7744

Max Act: 2.3004. Min Act: -0.0000

Data Index: 450888 (C4 (Web Text))

Max Activating Token Index: 977

Text #17

Max Range: 3.7744. Min Range: -3.7744

Max Act: 2.5476. Min Act: -0.0000

Data Index: 503659 (C4 (Web Text))

Max Activating Token Index: 125

Text #18

Max Range: 3.7744. Min Range: -3.7744

Max Act: 2.4207. Min Act: -0.0000

Data Index: 823762 (C4 (Web Text))

Max Activating Token Index: 123

Text #19

Max Range: 3.7744. Min Range: -3.7744

Max Act: 2.3998. Min Act: -0.0000

Data Index: 250075 (C4 (Web Text))

Max Activating Token Index: 433