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

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

Neuron 5234 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3184. Min Range: -1.3184

Max Act: 1.3184. Min Act: -0.0000

Data Index: 1302491 (C4 (Web Text))

Max Activating Token Index: 204

Text #1

Max Range: 1.3184. Min Range: -1.3184

Max Act: 1.2599. Min Act: -0.0000

Data Index: 373247 (C4 (Web Text))

Max Activating Token Index: 791

Text #2

Max Range: 1.3184. Min Range: -1.3184

Max Act: 1.1513. Min Act: -0.0000

Data Index: 534921 (C4 (Web Text))

Max Activating Token Index: 557

Text #3

Max Range: 1.3184. Min Range: -1.3184

Max Act: 0.9389. Min Act: -0.0000

Data Index: 1067056 (C4 (Web Text))

Max Activating Token Index: 194

Text #4

Max Range: 1.3184. Min Range: -1.3184

Max Act: 0.9301. Min Act: -0.0000

Data Index: 1055165 (C4 (Web Text))

Max Activating Token Index: 340

Text #5

Max Range: 1.3184. Min Range: -1.3184

Max Act: 0.8699. Min Act: -0.0000

Data Index: 121605 (C4 (Web Text))

Max Activating Token Index: 744

Text #6

Max Range: 1.3184. Min Range: -1.3184

Max Act: 0.8861. Min Act: -0.0000

Data Index: 438698 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 1.3184. Min Range: -1.3184

Max Act: 0.8605. Min Act: -0.0000

Data Index: 1093050 (C4 (Web Text))

Max Activating Token Index: 250

Text #8

Max Range: 1.3184. Min Range: -1.3184

Max Act: 0.9250. Min Act: -0.0000

Data Index: 1312750 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 1.3184. Min Range: -1.3184

Max Act: 0.9233. Min Act: -0.0000

Data Index: 458668 (C4 (Web Text))

Max Activating Token Index: 642

Text #10

Max Range: 1.3184. Min Range: -1.3184

Max Act: 0.9074. Min Act: -0.0000

Data Index: 768171 (C4 (Web Text))

Max Activating Token Index: 672

Text #11

Max Range: 1.3184. Min Range: -1.3184

Max Act: 0.8067. Min Act: -0.0000

Data Index: 1179950 (C4 (Web Text))

Max Activating Token Index: 845

Text #12

Max Range: 1.3184. Min Range: -1.3184

Max Act: 0.7960. Min Act: -0.0000

Data Index: 1251711 (C4 (Web Text))

Max Activating Token Index: 747

Text #13

Max Range: 1.3184. Min Range: -1.3184

Max Act: 0.8547. Min Act: -0.0000

Data Index: 275292 (C4 (Web Text))

Max Activating Token Index: 439

Text #14

Max Range: 1.3184. Min Range: -1.3184

Max Act: 0.8370. Min Act: -0.0000

Data Index: 854681 (C4 (Web Text))

Max Activating Token Index: 322

Text #15

Max Range: 1.3184. Min Range: -1.3184

Max Act: 0.8438. Min Act: -0.0000

Data Index: 1025067 (C4 (Web Text))

Max Activating Token Index: 895

Text #16

Max Range: 1.3184. Min Range: -1.3184

Max Act: 0.8698. Min Act: -0.0000

Data Index: 473534 (C4 (Web Text))

Max Activating Token Index: 146

Text #17

Max Range: 1.3184. Min Range: -1.3184

Max Act: 0.8836. Min Act: -0.0000

Data Index: 886812 (C4 (Web Text))

Max Activating Token Index: 130

Text #18

Max Range: 1.3184. Min Range: -1.3184

Max Act: 0.8500. Min Act: -0.0000

Data Index: 806313 (C4 (Web Text))

Max Activating Token Index: 714

Text #19

Max Range: 1.3184. Min Range: -1.3184

Max Act: 0.8355. Min Act: -0.0000

Data Index: 189313 (C4 (Web Text))

Max Activating Token Index: 936