Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 197 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0119. Min Range: -1.0119

Max Act: 1.0119. Min Act: -0.0000

Data Index: 1214361 (C4 (Web Text))

Max Activating Token Index: 436

Text #1

Max Range: 1.0119. Min Range: -1.0119

Max Act: 0.9659. Min Act: -0.0000

Data Index: 912399 (C4 (Web Text))

Max Activating Token Index: 487

Text #2

Max Range: 1.0119. Min Range: -1.0119

Max Act: 0.9053. Min Act: -0.0000

Data Index: 1096643 (C4 (Web Text))

Max Activating Token Index: 260

Text #3

Max Range: 1.0119. Min Range: -1.0119

Max Act: 0.8882. Min Act: -0.0000

Data Index: 91446 (C4 (Web Text))

Max Activating Token Index: 900

Text #4

Max Range: 1.0119. Min Range: -1.0119

Max Act: 0.9059. Min Act: -0.0000

Data Index: 1349478 (C4 (Web Text))

Max Activating Token Index: 615

Text #5

Max Range: 1.0119. Min Range: -1.0119

Max Act: 0.8259. Min Act: -0.0000

Data Index: 53890 (C4 (Web Text))

Max Activating Token Index: 737

Text #6

Max Range: 1.0119. Min Range: -1.0119

Max Act: 0.8041. Min Act: -0.0000

Data Index: 27098 (C4 (Web Text))

Max Activating Token Index: 337

Text #7

Max Range: 1.0119. Min Range: -1.0119

Max Act: 0.7761. Min Act: -0.0000

Data Index: 848405 (C4 (Web Text))

Max Activating Token Index: 313

Text #8

Max Range: 1.0119. Min Range: -1.0119

Max Act: 0.7444. Min Act: -0.0000

Data Index: 871865 (C4 (Web Text))

Max Activating Token Index: 654

Text #9

Max Range: 1.0119. Min Range: -1.0119

Max Act: 0.7249. Min Act: -0.0000

Data Index: 1186468 (C4 (Web Text))

Max Activating Token Index: 788

Text #10

Max Range: 1.0119. Min Range: -1.0119

Max Act: 0.6763. Min Act: -0.0000

Data Index: 1324312 (C4 (Web Text))

Max Activating Token Index: 135

Text #11

Max Range: 1.0119. Min Range: -1.0119

Max Act: 0.7402. Min Act: -0.0000

Data Index: 1343656 (C4 (Web Text))

Max Activating Token Index: 868

Text #12

Max Range: 1.0119. Min Range: -1.0119

Max Act: 0.7147. Min Act: -0.0000

Data Index: 901613 (C4 (Web Text))

Max Activating Token Index: 403

Text #13

Max Range: 1.0119. Min Range: -1.0119

Max Act: 0.7160. Min Act: -0.0000

Data Index: 204434 (C4 (Web Text))

Max Activating Token Index: 471

Text #14

Max Range: 1.0119. Min Range: -1.0119

Max Act: 0.6866. Min Act: -0.0000

Data Index: 629989 (C4 (Web Text))

Max Activating Token Index: 153

Text #15

Max Range: 1.0119. Min Range: -1.0119

Max Act: 0.7107. Min Act: -0.0000

Data Index: 830653 (C4 (Web Text))

Max Activating Token Index: 773

Text #16

Max Range: 1.0119. Min Range: -1.0119

Max Act: 0.6790. Min Act: -0.0000

Data Index: 1220520 (C4 (Web Text))

Max Activating Token Index: 587

Text #17

Max Range: 1.0119. Min Range: -1.0119

Max Act: 0.6523. Min Act: -0.0000

Data Index: 1233149 (C4 (Web Text))

Max Activating Token Index: 111

Text #18

Max Range: 1.0119. Min Range: -1.0119

Max Act: 0.6704. Min Act: -0.0000

Data Index: 853615 (C4 (Web Text))

Max Activating Token Index: 852

Text #19

Max Range: 1.0119. Min Range: -1.0119

Max Act: 0.6785. Min Act: -0.0000

Data Index: 40569 (C4 (Web Text))

Max Activating Token Index: 140