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

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

Neuron 1804 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: 0.3885. Min Range: -0.3885

Max Act: 0.3885. Min Act: -0.0000

Data Index: 495787 (C4 (Web Text))

Max Activating Token Index: 264

Text #1

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.3059. Min Act: -0.0000

Data Index: 1094704 (C4 (Web Text))

Max Activating Token Index: 826

Text #2

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.2957. Min Act: -0.0000

Data Index: 676635 (C4 (Web Text))

Max Activating Token Index: 619

Text #3

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.2622. Min Act: -0.0000

Data Index: 1455927 (Python Code)

Max Activating Token Index: 943

Text #4

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.2533. Min Act: -0.0000

Data Index: 1214704 (C4 (Web Text))

Max Activating Token Index: 778

Text #5

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.2392. Min Act: -0.0000

Data Index: 1008695 (C4 (Web Text))

Max Activating Token Index: 796

Text #6

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.2120. Min Act: -0.0000

Data Index: 964624 (C4 (Web Text))

Max Activating Token Index: 634

Text #7

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.2083. Min Act: -0.0000

Data Index: 1133502 (C4 (Web Text))

Max Activating Token Index: 593

Text #8

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.2205. Min Act: -0.0000

Data Index: 1352556 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.2080. Min Act: -0.0000

Data Index: 1470801 (Python Code)

Max Activating Token Index: 363

Text #10

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.2041. Min Act: -0.0000

Data Index: 1553789 (Python Code)

Max Activating Token Index: 499

Text #11

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.1966. Min Act: -0.0000

Data Index: 178613 (C4 (Web Text))

Max Activating Token Index: 673

Text #12

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.1982. Min Act: -0.0000

Data Index: 428582 (C4 (Web Text))

Max Activating Token Index: 256

Text #13

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.1833. Min Act: -0.0001

Data Index: 1391847 (Python Code)

Max Activating Token Index: 360

Text #14

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.1903. Min Act: -0.0000

Data Index: 1263502 (C4 (Web Text))

Max Activating Token Index: 802

Text #15

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.1828. Min Act: -0.0000

Data Index: 1224871 (C4 (Web Text))

Max Activating Token Index: 802

Text #16

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.1735. Min Act: -0.0000

Data Index: 1536540 (Python Code)

Max Activating Token Index: 211

Text #17

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.1803. Min Act: -0.0000

Data Index: 1389326 (Python Code)

Max Activating Token Index: 865

Text #18

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.1731. Min Act: -0.0000

Data Index: 1631234 (Python Code)

Max Activating Token Index: 618

Text #19

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.1794. Min Act: -0.0000

Data Index: 446260 (C4 (Web Text))

Max Activating Token Index: 691