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

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

Neuron 2436 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0074. Min Range: -4.0074

Max Act: 4.0074. Min Act: -0.0000

Data Index: 1503769 (Python Code)

Max Activating Token Index: 420

Text #1

Max Range: 4.0074. Min Range: -4.0074

Max Act: 3.8141. Min Act: -0.0000

Data Index: 1095854 (C4 (Web Text))

Max Activating Token Index: 776

Text #2

Max Range: 4.0074. Min Range: -4.0074

Max Act: 3.7737. Min Act: -0.0000

Data Index: 908266 (C4 (Web Text))

Max Activating Token Index: 957

Text #3

Max Range: 4.0074. Min Range: -4.0074

Max Act: 3.1719. Min Act: -0.0000

Data Index: 476255 (C4 (Web Text))

Max Activating Token Index: 681

Text #4

Max Range: 4.0074. Min Range: -4.0074

Max Act: 3.1731. Min Act: -0.0000

Data Index: 860283 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 4.0074. Min Range: -4.0074

Max Act: 3.2890. Min Act: -0.0000

Data Index: 433902 (C4 (Web Text))

Max Activating Token Index: 974

Text #6

Max Range: 4.0074. Min Range: -4.0074

Max Act: 3.1076. Min Act: -0.0000

Data Index: 609563 (C4 (Web Text))

Max Activating Token Index: 268

Text #7

Max Range: 4.0074. Min Range: -4.0074

Max Act: 3.1651. Min Act: -0.0000

Data Index: 220036 (C4 (Web Text))

Max Activating Token Index: 605

Text #8

Max Range: 4.0074. Min Range: -4.0074

Max Act: 3.1402. Min Act: -0.0000

Data Index: 144392 (C4 (Web Text))

Max Activating Token Index: 734

Text #9

Max Range: 4.0074. Min Range: -4.0074

Max Act: 2.9664. Min Act: -0.0000

Data Index: 177251 (C4 (Web Text))

Max Activating Token Index: 321

Text #10

Max Range: 4.0074. Min Range: -4.0074

Max Act: 2.7308. Min Act: -0.0000

Data Index: 676161 (C4 (Web Text))

Max Activating Token Index: 771

Text #11

Max Range: 4.0074. Min Range: -4.0074

Max Act: 3.1321. Min Act: -0.0000

Data Index: 964380 (C4 (Web Text))

Max Activating Token Index: 391

Text #12

Max Range: 4.0074. Min Range: -4.0074

Max Act: 2.9367. Min Act: -0.0000

Data Index: 1367168 (Python Code)

Max Activating Token Index: 978

Text #13

Max Range: 4.0074. Min Range: -4.0074

Max Act: 3.1812. Min Act: -0.0000

Data Index: 45930 (C4 (Web Text))

Max Activating Token Index: 74

Text #14

Max Range: 4.0074. Min Range: -4.0074

Max Act: 3.0024. Min Act: -0.0000

Data Index: 1254723 (C4 (Web Text))

Max Activating Token Index: 220

Text #15

Max Range: 4.0074. Min Range: -4.0074

Max Act: 3.2535. Min Act: -0.0000

Data Index: 378408 (C4 (Web Text))

Max Activating Token Index: 314

Text #16

Max Range: 4.0074. Min Range: -4.0074

Max Act: 2.9757. Min Act: -0.0000

Data Index: 875289 (C4 (Web Text))

Max Activating Token Index: 179

Text #17

Max Range: 4.0074. Min Range: -4.0074

Max Act: 3.1143. Min Act: -0.0000

Data Index: 433615 (C4 (Web Text))

Max Activating Token Index: 138

Text #18

Max Range: 4.0074. Min Range: -4.0074

Max Act: 2.9560. Min Act: 0.0000

Data Index: 119019 (C4 (Web Text))

Max Activating Token Index: 495

Text #19

Max Range: 4.0074. Min Range: -4.0074

Max Act: 3.1053. Min Act: -0.0000

Data Index: 481944 (C4 (Web Text))

Max Activating Token Index: 885