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

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

Neuron 3173 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0222. Min Range: -4.0222

Max Act: 4.0222. Min Act: -0.0000

Data Index: 165397 (C4 (Web Text))

Max Activating Token Index: 420

Text #1

Max Range: 4.0222. Min Range: -4.0222

Max Act: 3.8757. Min Act: 0.0000

Data Index: 812631 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 4.0222. Min Range: -4.0222

Max Act: 3.7042. Min Act: 0.0000

Data Index: 308738 (C4 (Web Text))

Max Activating Token Index: 524

Text #3

Max Range: 4.0222. Min Range: -4.0222

Max Act: 3.4844. Min Act: -0.0000

Data Index: 1300388 (C4 (Web Text))

Max Activating Token Index: 782

Text #4

Max Range: 4.0222. Min Range: -4.0222

Max Act: 3.6504. Min Act: -0.0000

Data Index: 878709 (C4 (Web Text))

Max Activating Token Index: 295

Text #5

Max Range: 4.0222. Min Range: -4.0222

Max Act: 3.1583. Min Act: -0.0000

Data Index: 470541 (C4 (Web Text))

Max Activating Token Index: 353

Text #6

Max Range: 4.0222. Min Range: -4.0222

Max Act: 3.2267. Min Act: -0.0000

Data Index: 72189 (C4 (Web Text))

Max Activating Token Index: 485

Text #7

Max Range: 4.0222. Min Range: -4.0222

Max Act: 3.3803. Min Act: -0.0000

Data Index: 268544 (C4 (Web Text))

Max Activating Token Index: 860

Text #8

Max Range: 4.0222. Min Range: -4.0222

Max Act: 3.0454. Min Act: 0.0000

Data Index: 236192 (C4 (Web Text))

Max Activating Token Index: 834

Text #9

Max Range: 4.0222. Min Range: -4.0222

Max Act: 3.3782. Min Act: 0.0000

Data Index: 176081 (C4 (Web Text))

Max Activating Token Index: 365

Text #10

Max Range: 4.0222. Min Range: -4.0222

Max Act: 3.0338. Min Act: 0.0000

Data Index: 515532 (C4 (Web Text))

Max Activating Token Index: 191

Text #11

Max Range: 4.0222. Min Range: -4.0222

Max Act: 3.0804. Min Act: 0.0000

Data Index: 556853 (C4 (Web Text))

Max Activating Token Index: 527

Text #12

Max Range: 4.0222. Min Range: -4.0222

Max Act: 2.8560. Min Act: -0.0000

Data Index: 357265 (C4 (Web Text))

Max Activating Token Index: 742

Text #13

Max Range: 4.0222. Min Range: -4.0222

Max Act: 2.7305. Min Act: -0.0000

Data Index: 830234 (C4 (Web Text))

Max Activating Token Index: 656

Text #14

Max Range: 4.0222. Min Range: -4.0222

Max Act: 2.6981. Min Act: 0.0001

Data Index: 519055 (C4 (Web Text))

Max Activating Token Index: 447

Text #15

Max Range: 4.0222. Min Range: -4.0222

Max Act: 2.5055. Min Act: 0.0000

Data Index: 207441 (C4 (Web Text))

Max Activating Token Index: 177

Text #16

Max Range: 4.0222. Min Range: -4.0222

Max Act: 2.5709. Min Act: -0.0000

Data Index: 477586 (C4 (Web Text))

Max Activating Token Index: 875

Text #17

Max Range: 4.0222. Min Range: -4.0222

Max Act: 2.5486. Min Act: 0.0000

Data Index: 364918 (C4 (Web Text))

Max Activating Token Index: 98

Text #18

Max Range: 4.0222. Min Range: -4.0222

Max Act: 2.6557. Min Act: -0.0000

Data Index: 987292 (C4 (Web Text))

Max Activating Token Index: 417

Text #19

Max Range: 4.0222. Min Range: -4.0222

Max Act: 2.3818. Min Act: -0.0000

Data Index: 98099 (C4 (Web Text))

Max Activating Token Index: 528