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

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

Neuron 194 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.4124. Min Range: -7.4124

Max Act: 7.2059. Min Act: -0.0000

Data Index: 291717 (C4 (Web Text))

Max Activating Token Index: 671

Text #1

Max Range: 7.4124. Min Range: -7.4124

Max Act: 7.4124. Min Act: -0.0000

Data Index: 1039603 (C4 (Web Text))

Max Activating Token Index: 101

Text #2

Max Range: 7.4124. Min Range: -7.4124

Max Act: 7.2091. Min Act: -0.0000

Data Index: 663513 (C4 (Web Text))

Max Activating Token Index: 136

Text #3

Max Range: 7.4124. Min Range: -7.4124

Max Act: 6.9529. Min Act: -0.0000

Data Index: 1008242 (C4 (Web Text))

Max Activating Token Index: 865

Text #4

Max Range: 7.4124. Min Range: -7.4124

Max Act: 6.7546. Min Act: -0.0000

Data Index: 460364 (C4 (Web Text))

Max Activating Token Index: 218

Text #5

Max Range: 7.4124. Min Range: -7.4124

Max Act: 6.8119. Min Act: -0.0000

Data Index: 1174726 (C4 (Web Text))

Max Activating Token Index: 826

Text #6

Max Range: 7.4124. Min Range: -7.4124

Max Act: 6.7817. Min Act: -0.0000

Data Index: 119276 (C4 (Web Text))

Max Activating Token Index: 165

Text #7

Max Range: 7.4124. Min Range: -7.4124

Max Act: 6.4356. Min Act: -0.0000

Data Index: 1071382 (C4 (Web Text))

Max Activating Token Index: 144

Text #8

Max Range: 7.4124. Min Range: -7.4124

Max Act: 5.5412. Min Act: -0.0000

Data Index: 842862 (C4 (Web Text))

Max Activating Token Index: 676

Text #9

Max Range: 7.4124. Min Range: -7.4124

Max Act: 5.4504. Min Act: -0.0000

Data Index: 865160 (C4 (Web Text))

Max Activating Token Index: 952

Text #10

Max Range: 7.4124. Min Range: -7.4124

Max Act: 5.3237. Min Act: -0.0000

Data Index: 1399388 (Python Code)

Max Activating Token Index: 740

Text #11

Max Range: 7.4124. Min Range: -7.4124

Max Act: 5.2514. Min Act: -0.0000

Data Index: 377109 (C4 (Web Text))

Max Activating Token Index: 951

Text #12

Max Range: 7.4124. Min Range: -7.4124

Max Act: 5.2251. Min Act: -0.0000

Data Index: 952939 (C4 (Web Text))

Max Activating Token Index: 426

Text #13

Max Range: 7.4124. Min Range: -7.4124

Max Act: 5.4043. Min Act: -0.0000

Data Index: 1629635 (Python Code)

Max Activating Token Index: 1020

Text #14

Max Range: 7.4124. Min Range: -7.4124

Max Act: 4.9033. Min Act: -0.0000

Data Index: 39159 (C4 (Web Text))

Max Activating Token Index: 454

Text #15

Max Range: 7.4124. Min Range: -7.4124

Max Act: 5.0468. Min Act: -0.0000

Data Index: 566520 (C4 (Web Text))

Max Activating Token Index: 321

Text #16

Max Range: 7.4124. Min Range: -7.4124

Max Act: 5.0421. Min Act: -0.0000

Data Index: 1448709 (Python Code)

Max Activating Token Index: 702

Text #17

Max Range: 7.4124. Min Range: -7.4124

Max Act: 4.8333. Min Act: -0.0000

Data Index: 1653712 (Python Code)

Max Activating Token Index: 409

Text #18

Max Range: 7.4124. Min Range: -7.4124

Max Act: 4.9775. Min Act: -0.0000

Data Index: 1299622 (C4 (Web Text))

Max Activating Token Index: 629

Text #19

Max Range: 7.4124. Min Range: -7.4124

Max Act: 4.9589. Min Act: -0.0000

Data Index: 187239 (C4 (Web Text))

Max Activating Token Index: 277