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

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

Neuron 1748 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.3074. Min Act: -0.0000

Data Index: 1043241 (C4 (Web Text))

Max Activating Token Index: 527

Text #1

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.2812. Min Act: -0.0000

Data Index: 285195 (C4 (Web Text))

Max Activating Token Index: 545

Text #2

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.2836. Min Act: -0.0000

Data Index: 651890 (C4 (Web Text))

Max Activating Token Index: 444

Text #3

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.2532. Min Act: -0.0000

Data Index: 360735 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.2550. Min Act: -0.0000

Data Index: 329230 (C4 (Web Text))

Max Activating Token Index: 956

Text #5

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.2461. Min Act: -0.0000

Data Index: 305950 (C4 (Web Text))

Max Activating Token Index: 909

Text #6

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.2510. Min Act: -0.0000

Data Index: 1232791 (C4 (Web Text))

Max Activating Token Index: 111

Text #7

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.2442. Min Act: -0.0000

Data Index: 351935 (C4 (Web Text))

Max Activating Token Index: 886

Text #8

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.2312. Min Act: -0.0000

Data Index: 83013 (C4 (Web Text))

Max Activating Token Index: 612

Text #9

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.2353. Min Act: -0.0000

Data Index: 694502 (C4 (Web Text))

Max Activating Token Index: 309

Text #10

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.2438. Min Act: -0.0000

Data Index: 295891 (C4 (Web Text))

Max Activating Token Index: 309

Text #11

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.2563. Min Act: -0.0000

Data Index: 965365 (C4 (Web Text))

Max Activating Token Index: 774

Text #12

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.2480. Min Act: -0.0000

Data Index: 507391 (C4 (Web Text))

Max Activating Token Index: 894

Text #13

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.2312. Min Act: -0.0000

Data Index: 357979 (C4 (Web Text))

Max Activating Token Index: 890

Text #14

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.2268. Min Act: -0.0000

Data Index: 981692 (C4 (Web Text))

Max Activating Token Index: 427

Text #15

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.2322. Min Act: -0.0000

Data Index: 1023239 (C4 (Web Text))

Max Activating Token Index: 961

Text #16

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.2233. Min Act: -0.0000

Data Index: 779312 (C4 (Web Text))

Max Activating Token Index: 738

Text #17

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.2194. Min Act: -0.0000

Data Index: 610378 (C4 (Web Text))

Max Activating Token Index: 700

Text #18

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.2240. Min Act: -0.0000

Data Index: 355240 (C4 (Web Text))

Max Activating Token Index: 132

Text #19

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.2308. Min Act: -0.0000

Data Index: 113271 (C4 (Web Text))

Max Activating Token Index: 128