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

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

Neuron 4032 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: 4.1440. Min Range: -4.1440

Max Act: 4.1440. Min Act: -0.0000

Data Index: 731212 (C4 (Web Text))

Max Activating Token Index: 167

Text #1

Max Range: 4.1440. Min Range: -4.1440

Max Act: 3.8686. Min Act: -0.0000

Data Index: 1062385 (C4 (Web Text))

Max Activating Token Index: 865

Text #2

Max Range: 4.1440. Min Range: -4.1440

Max Act: 3.8281. Min Act: -0.0000

Data Index: 533639 (C4 (Web Text))

Max Activating Token Index: 668

Text #3

Max Range: 4.1440. Min Range: -4.1440

Max Act: 3.6293. Min Act: -0.0000

Data Index: 1020583 (C4 (Web Text))

Max Activating Token Index: 810

Text #4

Max Range: 4.1440. Min Range: -4.1440

Max Act: 3.6818. Min Act: -0.0000

Data Index: 556476 (C4 (Web Text))

Max Activating Token Index: 922

Text #5

Max Range: 4.1440. Min Range: -4.1440

Max Act: 3.3500. Min Act: -0.0000

Data Index: 250069 (C4 (Web Text))

Max Activating Token Index: 129

Text #6

Max Range: 4.1440. Min Range: -4.1440

Max Act: 3.1336. Min Act: -0.0000

Data Index: 864037 (C4 (Web Text))

Max Activating Token Index: 836

Text #7

Max Range: 4.1440. Min Range: -4.1440

Max Act: 3.7021. Min Act: -0.0000

Data Index: 101311 (C4 (Web Text))

Max Activating Token Index: 9

Text #8

Max Range: 4.1440. Min Range: -4.1440

Max Act: 3.5030. Min Act: -0.0000

Data Index: 1280782 (C4 (Web Text))

Max Activating Token Index: 259

Text #9

Max Range: 4.1440. Min Range: -4.1440

Max Act: 3.4640. Min Act: -0.0000

Data Index: 649543 (C4 (Web Text))

Max Activating Token Index: 308

Text #10

Max Range: 4.1440. Min Range: -4.1440

Max Act: 3.1256. Min Act: -0.0000

Data Index: 1168162 (C4 (Web Text))

Max Activating Token Index: 10

Text #11

Max Range: 4.1440. Min Range: -4.1440

Max Act: 2.8193. Min Act: -0.0000

Data Index: 714815 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 4.1440. Min Range: -4.1440

Max Act: 3.1786. Min Act: -0.0000

Data Index: 138500 (C4 (Web Text))

Max Activating Token Index: 103

Text #13

Max Range: 4.1440. Min Range: -4.1440

Max Act: 2.8694. Min Act: -0.0000

Data Index: 314622 (C4 (Web Text))

Max Activating Token Index: 76

Text #14

Max Range: 4.1440. Min Range: -4.1440

Max Act: 2.6413. Min Act: -0.0000

Data Index: 689520 (C4 (Web Text))

Max Activating Token Index: 155

Text #15

Max Range: 4.1440. Min Range: -4.1440

Max Act: 2.7554. Min Act: -0.0000

Data Index: 410079 (C4 (Web Text))

Max Activating Token Index: 398

Text #16

Max Range: 4.1440. Min Range: -4.1440

Max Act: 2.3030. Min Act: -0.0000

Data Index: 609620 (C4 (Web Text))

Max Activating Token Index: 256

Text #17

Max Range: 4.1440. Min Range: -4.1440

Max Act: 2.6141. Min Act: -0.0000

Data Index: 164572 (C4 (Web Text))

Max Activating Token Index: 521

Text #18

Max Range: 4.1440. Min Range: -4.1440

Max Act: 2.4974. Min Act: -0.0000

Data Index: 25445 (C4 (Web Text))

Max Activating Token Index: 622

Text #19

Max Range: 4.1440. Min Range: -4.1440

Max Act: 2.5529. Min Act: -0.0000

Data Index: 887082 (C4 (Web Text))

Max Activating Token Index: 852