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

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

Neuron 2703 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: 4.9882. Min Range: -4.9882

Max Act: 4.6564. Min Act: -0.0000

Data Index: 150239 (C4 (Web Text))

Max Activating Token Index: 418

Text #1

Max Range: 4.9882. Min Range: -4.9882

Max Act: 4.9882. Min Act: -0.0000

Data Index: 634477 (C4 (Web Text))

Max Activating Token Index: 118

Text #2

Max Range: 4.9882. Min Range: -4.9882

Max Act: 4.6862. Min Act: -0.0000

Data Index: 1300399 (C4 (Web Text))

Max Activating Token Index: 555

Text #3

Max Range: 4.9882. Min Range: -4.9882

Max Act: 4.4950. Min Act: -0.0000

Data Index: 532989 (C4 (Web Text))

Max Activating Token Index: 186

Text #4

Max Range: 4.9882. Min Range: -4.9882

Max Act: 4.2929. Min Act: -0.0000

Data Index: 1204497 (C4 (Web Text))

Max Activating Token Index: 531

Text #5

Max Range: 4.9882. Min Range: -4.9882

Max Act: 4.2442. Min Act: -0.0000

Data Index: 721199 (C4 (Web Text))

Max Activating Token Index: 838

Text #6

Max Range: 4.9882. Min Range: -4.9882

Max Act: 4.0083. Min Act: -0.0000

Data Index: 1057316 (C4 (Web Text))

Max Activating Token Index: 158

Text #7

Max Range: 4.9882. Min Range: -4.9882

Max Act: 4.0221. Min Act: -0.0000

Data Index: 424338 (C4 (Web Text))

Max Activating Token Index: 831

Text #8

Max Range: 4.9882. Min Range: -4.9882

Max Act: 3.5410. Min Act: -0.0000

Data Index: 1320056 (C4 (Web Text))

Max Activating Token Index: 127

Text #9

Max Range: 4.9882. Min Range: -4.9882

Max Act: 3.2280. Min Act: -0.0000

Data Index: 948449 (C4 (Web Text))

Max Activating Token Index: 896

Text #10

Max Range: 4.9882. Min Range: -4.9882

Max Act: 3.3376. Min Act: -0.0000

Data Index: 884494 (C4 (Web Text))

Max Activating Token Index: 970

Text #11

Max Range: 4.9882. Min Range: -4.9882

Max Act: 3.1805. Min Act: -0.0000

Data Index: 162354 (C4 (Web Text))

Max Activating Token Index: 880

Text #12

Max Range: 4.9882. Min Range: -4.9882

Max Act: 2.9378. Min Act: -0.0000

Data Index: 1055008 (C4 (Web Text))

Max Activating Token Index: 648

Text #13

Max Range: 4.9882. Min Range: -4.9882

Max Act: 2.9106. Min Act: -0.0000

Data Index: 885645 (C4 (Web Text))

Max Activating Token Index: 540

Text #14

Max Range: 4.9882. Min Range: -4.9882

Max Act: 2.8815. Min Act: -0.0000

Data Index: 16129 (C4 (Web Text))

Max Activating Token Index: 453

Text #15

Max Range: 4.9882. Min Range: -4.9882

Max Act: 3.2448. Min Act: -0.0000

Data Index: 166338 (C4 (Web Text))

Max Activating Token Index: 258

Text #16

Max Range: 4.9882. Min Range: -4.9882

Max Act: 2.6926. Min Act: -0.0000

Data Index: 222536 (C4 (Web Text))

Max Activating Token Index: 870

Text #17

Max Range: 4.9882. Min Range: -4.9882

Max Act: 2.6715. Min Act: -0.0000

Data Index: 944843 (C4 (Web Text))

Max Activating Token Index: 1008

Text #18

Max Range: 4.9882. Min Range: -4.9882

Max Act: 2.8315. Min Act: -0.0000

Data Index: 482301 (C4 (Web Text))

Max Activating Token Index: 46

Text #19

Max Range: 4.9882. Min Range: -4.9882

Max Act: 2.9302. Min Act: -0.0000

Data Index: 537777 (C4 (Web Text))

Max Activating Token Index: 521