Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3210 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.6784. Min Act: -0.0001

Data Index: 269479 (C4 (Web Text))

Max Activating Token Index: 560

Text #1

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.7130. Min Act: -0.0000

Data Index: 133544 (C4 (Web Text))

Max Activating Token Index: 828

Text #2

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.6816. Min Act: -0.0001

Data Index: 723083 (C4 (Web Text))

Max Activating Token Index: 894

Text #3

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.6391. Min Act: -0.0000

Data Index: 1207201 (C4 (Web Text))

Max Activating Token Index: 913

Text #4

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.6492. Min Act: -0.0000

Data Index: 1411210 (Python Code)

Max Activating Token Index: 988

Text #5

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.6264. Min Act: -0.0000

Data Index: 1145037 (C4 (Web Text))

Max Activating Token Index: 328

Text #6

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.6214. Min Act: -0.0001

Data Index: 853334 (C4 (Web Text))

Max Activating Token Index: 335

Text #7

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.6192. Min Act: -0.0000

Data Index: 1348197 (C4 (Web Text))

Max Activating Token Index: 828

Text #8

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.6678. Min Act: -0.0001

Data Index: 191012 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.5891. Min Act: -0.0000

Data Index: 1189287 (C4 (Web Text))

Max Activating Token Index: 874

Text #10

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.6945. Min Act: -0.0000

Data Index: 259222 (C4 (Web Text))

Max Activating Token Index: 769

Text #11

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.5893. Min Act: -0.0000

Data Index: 552678 (C4 (Web Text))

Max Activating Token Index: 897

Text #12

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.5999. Min Act: -0.0000

Data Index: 780651 (C4 (Web Text))

Max Activating Token Index: 647

Text #13

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.5667. Min Act: -0.0001

Data Index: 591124 (C4 (Web Text))

Max Activating Token Index: 976

Text #14

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.5700. Min Act: -0.0000

Data Index: 1640440 (Python Code)

Max Activating Token Index: 298

Text #15

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.5494. Min Act: -0.0001

Data Index: 1069727 (C4 (Web Text))

Max Activating Token Index: 253

Text #16

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.5646. Min Act: -0.0000

Data Index: 918882 (C4 (Web Text))

Max Activating Token Index: 449

Text #17

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.5760. Min Act: -0.0000

Data Index: 1395038 (Python Code)

Max Activating Token Index: 512

Text #18

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.5705. Min Act: -0.0000

Data Index: 149433 (C4 (Web Text))

Max Activating Token Index: 588

Text #19

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.5508. Min Act: -0.0000

Data Index: 270564 (C4 (Web Text))

Max Activating Token Index: 731