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

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

Neuron 5399 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: 0.7564. Min Range: -0.7564

Max Act: 0.7564. Min Act: -0.0000

Data Index: 31776 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 0.7564. Min Range: -0.7564

Max Act: 0.7137. Min Act: -0.0000

Data Index: 389796 (C4 (Web Text))

Max Activating Token Index: 975

Text #2

Max Range: 0.7564. Min Range: -0.7564

Max Act: 0.5721. Min Act: -0.0000

Data Index: 1180855 (C4 (Web Text))

Max Activating Token Index: 332

Text #3

Max Range: 0.7564. Min Range: -0.7564

Max Act: 0.5536. Min Act: 0.0000

Data Index: 45615 (C4 (Web Text))

Max Activating Token Index: 376

Text #4

Max Range: 0.7564. Min Range: -0.7564

Max Act: 0.4849. Min Act: -0.0000

Data Index: 941468 (C4 (Web Text))

Max Activating Token Index: 206

Text #5

Max Range: 0.7564. Min Range: -0.7564

Max Act: 0.6093. Min Act: -0.0000

Data Index: 69617 (C4 (Web Text))

Max Activating Token Index: 995

Text #6

Max Range: 0.7564. Min Range: -0.7564

Max Act: 0.5321. Min Act: -0.0000

Data Index: 7547 (C4 (Web Text))

Max Activating Token Index: 238

Text #7

Max Range: 0.7564. Min Range: -0.7564

Max Act: 0.5317. Min Act: -0.0000

Data Index: 566593 (C4 (Web Text))

Max Activating Token Index: 266

Text #8

Max Range: 0.7564. Min Range: -0.7564

Max Act: 0.4429. Min Act: 0.0000

Data Index: 566920 (C4 (Web Text))

Max Activating Token Index: 810

Text #9

Max Range: 0.7564. Min Range: -0.7564

Max Act: 0.4182. Min Act: -0.0000

Data Index: 589497 (C4 (Web Text))

Max Activating Token Index: 74

Text #10

Max Range: 0.7564. Min Range: -0.7564

Max Act: 0.4432. Min Act: -0.0000

Data Index: 295503 (C4 (Web Text))

Max Activating Token Index: 398

Text #11

Max Range: 0.7564. Min Range: -0.7564

Max Act: 0.4406. Min Act: -0.0000

Data Index: 909739 (C4 (Web Text))

Max Activating Token Index: 658

Text #12

Max Range: 0.7564. Min Range: -0.7564

Max Act: 0.3898. Min Act: -0.0000

Data Index: 963196 (C4 (Web Text))

Max Activating Token Index: 587

Text #13

Max Range: 0.7564. Min Range: -0.7564

Max Act: 0.3920. Min Act: -0.0000

Data Index: 163965 (C4 (Web Text))

Max Activating Token Index: 221

Text #14

Max Range: 0.7564. Min Range: -0.7564

Max Act: 0.4025. Min Act: -0.0000

Data Index: 1292002 (C4 (Web Text))

Max Activating Token Index: 250

Text #15

Max Range: 0.7564. Min Range: -0.7564

Max Act: 0.3585. Min Act: -0.0000

Data Index: 988690 (C4 (Web Text))

Max Activating Token Index: 783

Text #16

Max Range: 0.7564. Min Range: -0.7564

Max Act: 0.3991. Min Act: 0.0001

Data Index: 518504 (C4 (Web Text))

Max Activating Token Index: 306

Text #17

Max Range: 0.7564. Min Range: -0.7564

Max Act: 0.4012. Min Act: -0.0000

Data Index: 716525 (C4 (Web Text))

Max Activating Token Index: 385

Text #18

Max Range: 0.7564. Min Range: -0.7564

Max Act: 0.4183. Min Act: 0.0000

Data Index: 1203580 (C4 (Web Text))

Max Activating Token Index: 651

Text #19

Max Range: 0.7564. Min Range: -0.7564

Max Act: 0.3892. Min Act: -0.0000

Data Index: 680971 (C4 (Web Text))

Max Activating Token Index: 828