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

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

Neuron 4655 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6109. Min Range: -3.6109

Max Act: 3.6109. Min Act: -0.0000

Data Index: 1491677 (Python Code)

Max Activating Token Index: 974

Text #1

Max Range: 3.6109. Min Range: -3.6109

Max Act: 3.4992. Min Act: -0.0000

Data Index: 1397578 (Python Code)

Max Activating Token Index: 26

Text #2

Max Range: 3.6109. Min Range: -3.6109

Max Act: 3.3035. Min Act: -0.0000

Data Index: 1366371 (Python Code)

Max Activating Token Index: 354

Text #3

Max Range: 3.6109. Min Range: -3.6109

Max Act: 3.4583. Min Act: -0.0000

Data Index: 1575418 (Python Code)

Max Activating Token Index: 39

Text #4

Max Range: 3.6109. Min Range: -3.6109

Max Act: 3.4367. Min Act: -0.0000

Data Index: 1380111 (Python Code)

Max Activating Token Index: 128

Text #5

Max Range: 3.6109. Min Range: -3.6109

Max Act: 3.2752. Min Act: -0.0000

Data Index: 1372353 (Python Code)

Max Activating Token Index: 42

Text #6

Max Range: 3.6109. Min Range: -3.6109

Max Act: 3.2861. Min Act: -0.0000

Data Index: 1622520 (Python Code)

Max Activating Token Index: 937

Text #7

Max Range: 3.6109. Min Range: -3.6109

Max Act: 3.2295. Min Act: -0.0000

Data Index: 1656477 (Python Code)

Max Activating Token Index: 199

Text #8

Max Range: 3.6109. Min Range: -3.6109

Max Act: 3.3678. Min Act: -0.0000

Data Index: 1623061 (Python Code)

Max Activating Token Index: 841

Text #9

Max Range: 3.6109. Min Range: -3.6109

Max Act: 3.3623. Min Act: -0.0000

Data Index: 1654610 (Python Code)

Max Activating Token Index: 102

Text #10

Max Range: 3.6109. Min Range: -3.6109

Max Act: 3.3659. Min Act: -0.0000

Data Index: 1600878 (Python Code)

Max Activating Token Index: 24

Text #11

Max Range: 3.6109. Min Range: -3.6109

Max Act: 3.3388. Min Act: -0.0000

Data Index: 1534348 (Python Code)

Max Activating Token Index: 87

Text #12

Max Range: 3.6109. Min Range: -3.6109

Max Act: 3.4925. Min Act: -0.0000

Data Index: 1374154 (Python Code)

Max Activating Token Index: 51

Text #13

Max Range: 3.6109. Min Range: -3.6109

Max Act: 3.3293. Min Act: -0.0000

Data Index: 1403796 (Python Code)

Max Activating Token Index: 71

Text #14

Max Range: 3.6109. Min Range: -3.6109

Max Act: 3.1713. Min Act: -0.0000

Data Index: 1602980 (Python Code)

Max Activating Token Index: 226

Text #15

Max Range: 3.6109. Min Range: -3.6109

Max Act: 3.3123. Min Act: -0.0000

Data Index: 1634349 (Python Code)

Max Activating Token Index: 463

Text #16

Max Range: 3.6109. Min Range: -3.6109

Max Act: 3.4621. Min Act: -0.0000

Data Index: 1420459 (Python Code)

Max Activating Token Index: 701

Text #17

Max Range: 3.6109. Min Range: -3.6109

Max Act: 3.3122. Min Act: -0.0000

Data Index: 1647495 (Python Code)

Max Activating Token Index: 683

Text #18

Max Range: 3.6109. Min Range: -3.6109

Max Act: 3.4705. Min Act: -0.0000

Data Index: 1362193 (Python Code)

Max Activating Token Index: 756

Text #19

Max Range: 3.6109. Min Range: -3.6109

Max Act: 3.2924. Min Act: -0.0000

Data Index: 1639785 (Python Code)

Max Activating Token Index: 214