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

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

Neuron 5240 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: 2.1173. Min Range: -2.1173

Max Act: 1.9634. Min Act: -0.0000

Data Index: 504330 (C4 (Web Text))

Max Activating Token Index: 166

Text #1

Max Range: 2.1173. Min Range: -2.1173

Max Act: 2.0206. Min Act: -0.0000

Data Index: 1593560 (Python Code)

Max Activating Token Index: 586

Text #2

Max Range: 2.1173. Min Range: -2.1173

Max Act: 2.1173. Min Act: -0.0000

Data Index: 1521438 (Python Code)

Max Activating Token Index: 98

Text #3

Max Range: 2.1173. Min Range: -2.1173

Max Act: 2.0055. Min Act: -0.0000

Data Index: 1370780 (Python Code)

Max Activating Token Index: 264

Text #4

Max Range: 2.1173. Min Range: -2.1173

Max Act: 2.0018. Min Act: -0.0000

Data Index: 1508480 (Python Code)

Max Activating Token Index: 994

Text #5

Max Range: 2.1173. Min Range: -2.1173

Max Act: 1.9748. Min Act: -0.0000

Data Index: 451126 (C4 (Web Text))

Max Activating Token Index: 955

Text #6

Max Range: 2.1173. Min Range: -2.1173

Max Act: 2.0728. Min Act: -0.0000

Data Index: 62834 (C4 (Web Text))

Max Activating Token Index: 610

Text #7

Max Range: 2.1173. Min Range: -2.1173

Max Act: 1.9796. Min Act: -0.0000

Data Index: 1455240 (Python Code)

Max Activating Token Index: 946

Text #8

Max Range: 2.1173. Min Range: -2.1173

Max Act: 1.9856. Min Act: -0.0000

Data Index: 1378894 (Python Code)

Max Activating Token Index: 110

Text #9

Max Range: 2.1173. Min Range: -2.1173

Max Act: 1.9862. Min Act: -0.0000

Data Index: 1591138 (Python Code)

Max Activating Token Index: 421

Text #10

Max Range: 2.1173. Min Range: -2.1173

Max Act: 1.9244. Min Act: -0.0000

Data Index: 1527052 (Python Code)

Max Activating Token Index: 166

Text #11

Max Range: 2.1173. Min Range: -2.1173

Max Act: 1.9167. Min Act: -0.0000

Data Index: 1292010 (C4 (Web Text))

Max Activating Token Index: 457

Text #12

Max Range: 2.1173. Min Range: -2.1173

Max Act: 1.7627. Min Act: -0.0000

Data Index: 1411884 (Python Code)

Max Activating Token Index: 658

Text #13

Max Range: 2.1173. Min Range: -2.1173

Max Act: 1.7716. Min Act: -0.0000

Data Index: 154707 (C4 (Web Text))

Max Activating Token Index: 89

Text #14

Max Range: 2.1173. Min Range: -2.1173

Max Act: 1.9639. Min Act: -0.0000

Data Index: 1392220 (Python Code)

Max Activating Token Index: 678

Text #15

Max Range: 2.1173. Min Range: -2.1173

Max Act: 1.9255. Min Act: -0.0000

Data Index: 1489322 (Python Code)

Max Activating Token Index: 970

Text #16

Max Range: 2.1173. Min Range: -2.1173

Max Act: 1.8261. Min Act: -0.0000

Data Index: 1528228 (Python Code)

Max Activating Token Index: 468

Text #17

Max Range: 2.1173. Min Range: -2.1173

Max Act: 1.8244. Min Act: -0.0000

Data Index: 1457447 (Python Code)

Max Activating Token Index: 335

Text #18

Max Range: 2.1173. Min Range: -2.1173

Max Act: 1.7996. Min Act: -0.0000

Data Index: 1594774 (Python Code)

Max Activating Token Index: 982

Text #19

Max Range: 2.1173. Min Range: -2.1173

Max Act: 1.7877. Min Act: -0.0000

Data Index: 1456943 (Python Code)

Max Activating Token Index: 20