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

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

Neuron 3963 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1947. Min Range: -4.1947

Max Act: 4.1947. Min Act: -0.0000

Data Index: 138705 (C4 (Web Text))

Max Activating Token Index: 842

Text #1

Max Range: 4.1947. Min Range: -4.1947

Max Act: 3.4448. Min Act: -0.0000

Data Index: 970902 (C4 (Web Text))

Max Activating Token Index: 466

Text #2

Max Range: 4.1947. Min Range: -4.1947

Max Act: 3.4062. Min Act: -0.0000

Data Index: 1231209 (C4 (Web Text))

Max Activating Token Index: 750

Text #3

Max Range: 4.1947. Min Range: -4.1947

Max Act: 3.1770. Min Act: -0.0000

Data Index: 503191 (C4 (Web Text))

Max Activating Token Index: 704

Text #4

Max Range: 4.1947. Min Range: -4.1947

Max Act: 3.1808. Min Act: -0.0000

Data Index: 677705 (C4 (Web Text))

Max Activating Token Index: 861

Text #5

Max Range: 4.1947. Min Range: -4.1947

Max Act: 3.1513. Min Act: -0.0000

Data Index: 76000 (C4 (Web Text))

Max Activating Token Index: 975

Text #6

Max Range: 4.1947. Min Range: -4.1947

Max Act: 2.9786. Min Act: -0.0000

Data Index: 546131 (C4 (Web Text))

Max Activating Token Index: 233

Text #7

Max Range: 4.1947. Min Range: -4.1947

Max Act: 2.9128. Min Act: -0.0000

Data Index: 684536 (C4 (Web Text))

Max Activating Token Index: 617

Text #8

Max Range: 4.1947. Min Range: -4.1947

Max Act: 3.2269. Min Act: -0.0000

Data Index: 63863 (C4 (Web Text))

Max Activating Token Index: 895

Text #9

Max Range: 4.1947. Min Range: -4.1947

Max Act: 3.0207. Min Act: -0.0000

Data Index: 578225 (C4 (Web Text))

Max Activating Token Index: 321

Text #10

Max Range: 4.1947. Min Range: -4.1947

Max Act: 2.9523. Min Act: -0.0000

Data Index: 876712 (C4 (Web Text))

Max Activating Token Index: 907

Text #11

Max Range: 4.1947. Min Range: -4.1947

Max Act: 2.9135. Min Act: -0.0000

Data Index: 102771 (C4 (Web Text))

Max Activating Token Index: 208

Text #12

Max Range: 4.1947. Min Range: -4.1947

Max Act: 2.8724. Min Act: -0.0000

Data Index: 62537 (C4 (Web Text))

Max Activating Token Index: 850

Text #13

Max Range: 4.1947. Min Range: -4.1947

Max Act: 2.8521. Min Act: -0.0000

Data Index: 409048 (C4 (Web Text))

Max Activating Token Index: 1011

Text #14

Max Range: 4.1947. Min Range: -4.1947

Max Act: 2.7067. Min Act: -0.0000

Data Index: 914750 (C4 (Web Text))

Max Activating Token Index: 134

Text #15

Max Range: 4.1947. Min Range: -4.1947

Max Act: 2.9666. Min Act: -0.0000

Data Index: 199017 (C4 (Web Text))

Max Activating Token Index: 570

Text #16

Max Range: 4.1947. Min Range: -4.1947

Max Act: 2.7016. Min Act: -0.0000

Data Index: 1177423 (C4 (Web Text))

Max Activating Token Index: 198

Text #17

Max Range: 4.1947. Min Range: -4.1947

Max Act: 2.6714. Min Act: -0.0000

Data Index: 1298292 (C4 (Web Text))

Max Activating Token Index: 281

Text #18

Max Range: 4.1947. Min Range: -4.1947

Max Act: 2.9691. Min Act: -0.0000

Data Index: 322862 (C4 (Web Text))

Max Activating Token Index: 671

Text #19

Max Range: 4.1947. Min Range: -4.1947

Max Act: 2.8183. Min Act: -0.0000

Data Index: 144939 (C4 (Web Text))

Max Activating Token Index: 62