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

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

Neuron 2429 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: 1.3959. Min Range: -1.3959

Max Act: 1.3959. Min Act: -0.0000

Data Index: 1531206 (Python Code)

Max Activating Token Index: 903

Text #1

Max Range: 1.3959. Min Range: -1.3959

Max Act: 1.2334. Min Act: -0.0000

Data Index: 878433 (C4 (Web Text))

Max Activating Token Index: 86

Text #2

Max Range: 1.3959. Min Range: -1.3959

Max Act: 1.0415. Min Act: -0.0000

Data Index: 1468849 (Python Code)

Max Activating Token Index: 561

Text #3

Max Range: 1.3959. Min Range: -1.3959

Max Act: 0.9904. Min Act: -0.0000

Data Index: 278373 (C4 (Web Text))

Max Activating Token Index: 352

Text #4

Max Range: 1.3959. Min Range: -1.3959

Max Act: 1.0423. Min Act: -0.0000

Data Index: 994280 (C4 (Web Text))

Max Activating Token Index: 428

Text #5

Max Range: 1.3959. Min Range: -1.3959

Max Act: 1.0271. Min Act: -0.0000

Data Index: 117002 (C4 (Web Text))

Max Activating Token Index: 739

Text #6

Max Range: 1.3959. Min Range: -1.3959

Max Act: 0.9799. Min Act: -0.0000

Data Index: 1560063 (Python Code)

Max Activating Token Index: 1006

Text #7

Max Range: 1.3959. Min Range: -1.3959

Max Act: 1.0171. Min Act: -0.0000

Data Index: 409370 (C4 (Web Text))

Max Activating Token Index: 979

Text #8

Max Range: 1.3959. Min Range: -1.3959

Max Act: 1.0123. Min Act: -0.0000

Data Index: 1367653 (Python Code)

Max Activating Token Index: 245

Text #9

Max Range: 1.3959. Min Range: -1.3959

Max Act: 0.9533. Min Act: -0.0000

Data Index: 1367486 (Python Code)

Max Activating Token Index: 702

Text #10

Max Range: 1.3959. Min Range: -1.3959

Max Act: 0.9792. Min Act: -0.0000

Data Index: 312322 (C4 (Web Text))

Max Activating Token Index: 801

Text #11

Max Range: 1.3959. Min Range: -1.3959

Max Act: 0.9806. Min Act: -0.0000

Data Index: 1522552 (Python Code)

Max Activating Token Index: 1011

Text #12

Max Range: 1.3959. Min Range: -1.3959

Max Act: 1.0097. Min Act: -0.0000

Data Index: 151514 (C4 (Web Text))

Max Activating Token Index: 961

Text #13

Max Range: 1.3959. Min Range: -1.3959

Max Act: 0.9737. Min Act: -0.0000

Data Index: 655442 (C4 (Web Text))

Max Activating Token Index: 225

Text #14

Max Range: 1.3959. Min Range: -1.3959

Max Act: 0.9699. Min Act: -0.0000

Data Index: 522150 (C4 (Web Text))

Max Activating Token Index: 901

Text #15

Max Range: 1.3959. Min Range: -1.3959

Max Act: 0.9588. Min Act: -0.0000

Data Index: 426207 (C4 (Web Text))

Max Activating Token Index: 675

Text #16

Max Range: 1.3959. Min Range: -1.3959

Max Act: 0.9665. Min Act: -0.0000

Data Index: 1178265 (C4 (Web Text))

Max Activating Token Index: 289

Text #17

Max Range: 1.3959. Min Range: -1.3959

Max Act: 0.9728. Min Act: -0.0000

Data Index: 1446548 (Python Code)

Max Activating Token Index: 738

Text #18

Max Range: 1.3959. Min Range: -1.3959

Max Act: 0.9422. Min Act: -0.0000

Data Index: 112994 (C4 (Web Text))

Max Activating Token Index: 596

Text #19

Max Range: 1.3959. Min Range: -1.3959

Max Act: 0.9535. Min Act: -0.0000

Data Index: 1496435 (Python Code)

Max Activating Token Index: 1011