Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4168 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.4922. Min Range: -4.4922

Max Act: 4.4922. Min Act: -0.0000

Data Index: 271755 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 4.4922. Min Range: -4.4922

Max Act: 4.0502. Min Act: -0.0000

Data Index: 1213427 (C4 (Web Text))

Max Activating Token Index: 270

Text #2

Max Range: 4.4922. Min Range: -4.4922

Max Act: 4.1135. Min Act: -0.0000

Data Index: 1283752 (C4 (Web Text))

Max Activating Token Index: 356

Text #3

Max Range: 4.4922. Min Range: -4.4922

Max Act: 3.8610. Min Act: -0.0000

Data Index: 400213 (C4 (Web Text))

Max Activating Token Index: 933

Text #4

Max Range: 4.4922. Min Range: -4.4922

Max Act: 3.8527. Min Act: -0.0000

Data Index: 1119541 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 4.4922. Min Range: -4.4922

Max Act: 3.5142. Min Act: -0.0000

Data Index: 667228 (C4 (Web Text))

Max Activating Token Index: 688

Text #6

Max Range: 4.4922. Min Range: -4.4922

Max Act: 3.3540. Min Act: -0.0000

Data Index: 65080 (C4 (Web Text))

Max Activating Token Index: 837

Text #7

Max Range: 4.4922. Min Range: -4.4922

Max Act: 3.5687. Min Act: -0.0000

Data Index: 550657 (C4 (Web Text))

Max Activating Token Index: 797

Text #8

Max Range: 4.4922. Min Range: -4.4922

Max Act: 3.3921. Min Act: -0.0000

Data Index: 158127 (C4 (Web Text))

Max Activating Token Index: 327

Text #9

Max Range: 4.4922. Min Range: -4.4922

Max Act: 3.2265. Min Act: -0.0000

Data Index: 1315401 (C4 (Web Text))

Max Activating Token Index: 163

Text #10

Max Range: 4.4922. Min Range: -4.4922

Max Act: 3.5052. Min Act: -0.0000

Data Index: 293208 (C4 (Web Text))

Max Activating Token Index: 167

Text #11

Max Range: 4.4922. Min Range: -4.4922

Max Act: 3.2244. Min Act: -0.0000

Data Index: 223652 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 4.4922. Min Range: -4.4922

Max Act: 2.9859. Min Act: -0.0000

Data Index: 693607 (C4 (Web Text))

Max Activating Token Index: 567

Text #13

Max Range: 4.4922. Min Range: -4.4922

Max Act: 3.1002. Min Act: -0.0000

Data Index: 626467 (C4 (Web Text))

Max Activating Token Index: 203

Text #14

Max Range: 4.4922. Min Range: -4.4922

Max Act: 3.0886. Min Act: -0.0000

Data Index: 710435 (C4 (Web Text))

Max Activating Token Index: 631

Text #15

Max Range: 4.4922. Min Range: -4.4922

Max Act: 3.0244. Min Act: -0.0000

Data Index: 1250839 (C4 (Web Text))

Max Activating Token Index: 147

Text #16

Max Range: 4.4922. Min Range: -4.4922

Max Act: 3.0184. Min Act: -0.0000

Data Index: 239291 (C4 (Web Text))

Max Activating Token Index: 359

Text #17

Max Range: 4.4922. Min Range: -4.4922

Max Act: 2.8786. Min Act: -0.0000

Data Index: 1277282 (C4 (Web Text))

Max Activating Token Index: 292

Text #18

Max Range: 4.4922. Min Range: -4.4922

Max Act: 2.9814. Min Act: -0.0000

Data Index: 346229 (C4 (Web Text))

Max Activating Token Index: 552

Text #19

Max Range: 4.4922. Min Range: -4.4922

Max Act: 3.1207. Min Act: -0.0000

Data Index: 742528 (C4 (Web Text))

Max Activating Token Index: 164