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

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

Neuron 992 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6259. Min Range: -3.6259

Max Act: 3.5249. Min Act: -0.0001

Data Index: 73773 (C4 (Web Text))

Max Activating Token Index: 834

Text #1

Max Range: 3.6259. Min Range: -3.6259

Max Act: 3.6259. Min Act: -0.0001

Data Index: 879398 (C4 (Web Text))

Max Activating Token Index: 70

Text #2

Max Range: 3.6259. Min Range: -3.6259

Max Act: 3.5826. Min Act: -0.0001

Data Index: 684658 (C4 (Web Text))

Max Activating Token Index: 689

Text #3

Max Range: 3.6259. Min Range: -3.6259

Max Act: 3.3808. Min Act: -0.0001

Data Index: 1277674 (C4 (Web Text))

Max Activating Token Index: 129

Text #4

Max Range: 3.6259. Min Range: -3.6259

Max Act: 3.3510. Min Act: -0.0001

Data Index: 490404 (C4 (Web Text))

Max Activating Token Index: 400

Text #5

Max Range: 3.6259. Min Range: -3.6259

Max Act: 3.2173. Min Act: -0.0001

Data Index: 84834 (C4 (Web Text))

Max Activating Token Index: 436

Text #6

Max Range: 3.6259. Min Range: -3.6259

Max Act: 2.9120. Min Act: -0.0001

Data Index: 658721 (C4 (Web Text))

Max Activating Token Index: 503

Text #7

Max Range: 3.6259. Min Range: -3.6259

Max Act: 3.1946. Min Act: -0.0000

Data Index: 1233877 (C4 (Web Text))

Max Activating Token Index: 858

Text #8

Max Range: 3.6259. Min Range: -3.6259

Max Act: 2.9375. Min Act: -0.0001

Data Index: 1156130 (C4 (Web Text))

Max Activating Token Index: 728

Text #9

Max Range: 3.6259. Min Range: -3.6259

Max Act: 2.7314. Min Act: -0.0001

Data Index: 302912 (C4 (Web Text))

Max Activating Token Index: 274

Text #10

Max Range: 3.6259. Min Range: -3.6259

Max Act: 2.7441. Min Act: -0.0001

Data Index: 408400 (C4 (Web Text))

Max Activating Token Index: 1004

Text #11

Max Range: 3.6259. Min Range: -3.6259

Max Act: 2.6800. Min Act: -0.0001

Data Index: 1326333 (C4 (Web Text))

Max Activating Token Index: 848

Text #12

Max Range: 3.6259. Min Range: -3.6259

Max Act: 2.7444. Min Act: -0.0001

Data Index: 872903 (C4 (Web Text))

Max Activating Token Index: 808

Text #13

Max Range: 3.6259. Min Range: -3.6259

Max Act: 2.6096. Min Act: -0.0001

Data Index: 1170831 (C4 (Web Text))

Max Activating Token Index: 170

Text #14

Max Range: 3.6259. Min Range: -3.6259

Max Act: 2.7250. Min Act: -0.0001

Data Index: 347333 (C4 (Web Text))

Max Activating Token Index: 965

Text #15

Max Range: 3.6259. Min Range: -3.6259

Max Act: 2.8051. Min Act: -0.0001

Data Index: 906765 (C4 (Web Text))

Max Activating Token Index: 15

Text #16

Max Range: 3.6259. Min Range: -3.6259

Max Act: 2.9444. Min Act: -0.0001

Data Index: 162291 (C4 (Web Text))

Max Activating Token Index: 330

Text #17

Max Range: 3.6259. Min Range: -3.6259

Max Act: 2.8185. Min Act: -0.0000

Data Index: 494817 (C4 (Web Text))

Max Activating Token Index: 11

Text #18

Max Range: 3.6259. Min Range: -3.6259

Max Act: 2.8016. Min Act: -0.0001

Data Index: 1037418 (C4 (Web Text))

Max Activating Token Index: 885

Text #19

Max Range: 3.6259. Min Range: -3.6259

Max Act: 2.6377. Min Act: -0.0001

Data Index: 972505 (C4 (Web Text))

Max Activating Token Index: 9