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

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

Neuron 4616 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1184. Min Range: -2.1184

Max Act: 2.1184. Min Act: -0.0000

Data Index: 335004 (C4 (Web Text))

Max Activating Token Index: 139

Text #1

Max Range: 2.1184. Min Range: -2.1184

Max Act: 2.0763. Min Act: -0.0000

Data Index: 534852 (C4 (Web Text))

Max Activating Token Index: 219

Text #2

Max Range: 2.1184. Min Range: -2.1184

Max Act: 1.8907. Min Act: -0.0000

Data Index: 990984 (C4 (Web Text))

Max Activating Token Index: 880

Text #3

Max Range: 2.1184. Min Range: -2.1184

Max Act: 1.8493. Min Act: -0.0000

Data Index: 266619 (C4 (Web Text))

Max Activating Token Index: 59

Text #4

Max Range: 2.1184. Min Range: -2.1184

Max Act: 1.9248. Min Act: -0.0000

Data Index: 1117900 (C4 (Web Text))

Max Activating Token Index: 634

Text #5

Max Range: 2.1184. Min Range: -2.1184

Max Act: 1.7939. Min Act: -0.0000

Data Index: 570363 (C4 (Web Text))

Max Activating Token Index: 163

Text #6

Max Range: 2.1184. Min Range: -2.1184

Max Act: 1.8796. Min Act: -0.0000

Data Index: 914465 (C4 (Web Text))

Max Activating Token Index: 154

Text #7

Max Range: 2.1184. Min Range: -2.1184

Max Act: 1.8634. Min Act: -0.0000

Data Index: 1240408 (C4 (Web Text))

Max Activating Token Index: 165

Text #8

Max Range: 2.1184. Min Range: -2.1184

Max Act: 1.8533. Min Act: -0.0000

Data Index: 602444 (C4 (Web Text))

Max Activating Token Index: 538

Text #9

Max Range: 2.1184. Min Range: -2.1184

Max Act: 1.8384. Min Act: -0.0000

Data Index: 591666 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 2.1184. Min Range: -2.1184

Max Act: 1.7844. Min Act: -0.0000

Data Index: 768125 (C4 (Web Text))

Max Activating Token Index: 103

Text #11

Max Range: 2.1184. Min Range: -2.1184

Max Act: 1.8855. Min Act: -0.0000

Data Index: 624584 (C4 (Web Text))

Max Activating Token Index: 917

Text #12

Max Range: 2.1184. Min Range: -2.1184

Max Act: 1.7966. Min Act: -0.0000

Data Index: 75092 (C4 (Web Text))

Max Activating Token Index: 255

Text #13

Max Range: 2.1184. Min Range: -2.1184

Max Act: 1.7420. Min Act: -0.0000

Data Index: 1048668 (C4 (Web Text))

Max Activating Token Index: 981

Text #14

Max Range: 2.1184. Min Range: -2.1184

Max Act: 1.7459. Min Act: -0.0000

Data Index: 9073 (C4 (Web Text))

Max Activating Token Index: 651

Text #15

Max Range: 2.1184. Min Range: -2.1184

Max Act: 1.7318. Min Act: -0.0000

Data Index: 257222 (C4 (Web Text))

Max Activating Token Index: 978

Text #16

Max Range: 2.1184. Min Range: -2.1184

Max Act: 1.7205. Min Act: -0.0000

Data Index: 487057 (C4 (Web Text))

Max Activating Token Index: 56

Text #17

Max Range: 2.1184. Min Range: -2.1184

Max Act: 1.8330. Min Act: -0.0000

Data Index: 1046069 (C4 (Web Text))

Max Activating Token Index: 579

Text #18

Max Range: 2.1184. Min Range: -2.1184

Max Act: 1.7136. Min Act: -0.0000

Data Index: 75878 (C4 (Web Text))

Max Activating Token Index: 18

Text #19

Max Range: 2.1184. Min Range: -2.1184

Max Act: 1.6213. Min Act: -0.0000

Data Index: 70794 (C4 (Web Text))

Max Activating Token Index: 682