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

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

Neuron 4182 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3926. Min Range: -1.3926

Max Act: 1.3926. Min Act: -0.0000

Data Index: 814820 (C4 (Web Text))

Max Activating Token Index: 877

Text #1

Max Range: 1.3926. Min Range: -1.3926

Max Act: 1.0002. Min Act: -0.0000

Data Index: 324899 (C4 (Web Text))

Max Activating Token Index: 1015

Text #2

Max Range: 1.3926. Min Range: -1.3926

Max Act: 1.0178. Min Act: -0.0000

Data Index: 1081735 (C4 (Web Text))

Max Activating Token Index: 560

Text #3

Max Range: 1.3926. Min Range: -1.3926

Max Act: 0.9736. Min Act: -0.0000

Data Index: 1291958 (C4 (Web Text))

Max Activating Token Index: 905

Text #4

Max Range: 1.3926. Min Range: -1.3926

Max Act: 0.9420. Min Act: -0.0000

Data Index: 1442407 (Python Code)

Max Activating Token Index: 819

Text #5

Max Range: 1.3926. Min Range: -1.3926

Max Act: 0.9245. Min Act: -0.0000

Data Index: 1563912 (Python Code)

Max Activating Token Index: 843

Text #6

Max Range: 1.3926. Min Range: -1.3926

Max Act: 0.9181. Min Act: -0.0000

Data Index: 638442 (C4 (Web Text))

Max Activating Token Index: 41

Text #7

Max Range: 1.3926. Min Range: -1.3926

Max Act: 0.9226. Min Act: -0.0000

Data Index: 257023 (C4 (Web Text))

Max Activating Token Index: 178

Text #8

Max Range: 1.3926. Min Range: -1.3926

Max Act: 0.9188. Min Act: -0.0000

Data Index: 719156 (C4 (Web Text))

Max Activating Token Index: 672

Text #9

Max Range: 1.3926. Min Range: -1.3926

Max Act: 0.9877. Min Act: -0.0000

Data Index: 1307454 (C4 (Web Text))

Max Activating Token Index: 435

Text #10

Max Range: 1.3926. Min Range: -1.3926

Max Act: 0.9182. Min Act: -0.0000

Data Index: 185140 (C4 (Web Text))

Max Activating Token Index: 364

Text #11

Max Range: 1.3926. Min Range: -1.3926

Max Act: 0.8834. Min Act: -0.0000

Data Index: 885388 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 1.3926. Min Range: -1.3926

Max Act: 0.9089. Min Act: -0.0000

Data Index: 1010588 (C4 (Web Text))

Max Activating Token Index: 441

Text #13

Max Range: 1.3926. Min Range: -1.3926

Max Act: 0.9381. Min Act: -0.0000

Data Index: 1150509 (C4 (Web Text))

Max Activating Token Index: 762

Text #14

Max Range: 1.3926. Min Range: -1.3926

Max Act: 0.9173. Min Act: -0.0000

Data Index: 31685 (C4 (Web Text))

Max Activating Token Index: 989

Text #15

Max Range: 1.3926. Min Range: -1.3926

Max Act: 0.8150. Min Act: -0.0000

Data Index: 1045313 (C4 (Web Text))

Max Activating Token Index: 421

Text #16

Max Range: 1.3926. Min Range: -1.3926

Max Act: 0.7870. Min Act: -0.0000

Data Index: 1173319 (C4 (Web Text))

Max Activating Token Index: 967

Text #17

Max Range: 1.3926. Min Range: -1.3926

Max Act: 0.8112. Min Act: -0.0000

Data Index: 1181434 (C4 (Web Text))

Max Activating Token Index: 92

Text #18

Max Range: 1.3926. Min Range: -1.3926

Max Act: 0.8423. Min Act: -0.0000

Data Index: 139067 (C4 (Web Text))

Max Activating Token Index: 510

Text #19

Max Range: 1.3926. Min Range: -1.3926

Max Act: 0.7600. Min Act: -0.0000

Data Index: 403594 (C4 (Web Text))

Max Activating Token Index: 111