Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 214 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.7250. Min Act: -0.0001

Data Index: 789513 (C4 (Web Text))

Max Activating Token Index: 303

Text #1

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.6832. Min Act: -0.0001

Data Index: 37727 (C4 (Web Text))

Max Activating Token Index: 736

Text #2

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.6425. Min Act: -0.0001

Data Index: 22782 (C4 (Web Text))

Max Activating Token Index: 982

Text #3

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.6337. Min Act: -0.0001

Data Index: 1351657 (C4 (Web Text))

Max Activating Token Index: 1017

Text #4

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.6544. Min Act: -0.0001

Data Index: 403202 (C4 (Web Text))

Max Activating Token Index: 140

Text #5

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.7104. Min Act: -0.0001

Data Index: 1213060 (C4 (Web Text))

Max Activating Token Index: 763

Text #6

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.5983. Min Act: -0.0001

Data Index: 943897 (C4 (Web Text))

Max Activating Token Index: 833

Text #7

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.5989. Min Act: -0.0001

Data Index: 1060108 (C4 (Web Text))

Max Activating Token Index: 781

Text #8

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.5950. Min Act: -0.0001

Data Index: 302687 (C4 (Web Text))

Max Activating Token Index: 700

Text #9

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.5766. Min Act: -0.0001

Data Index: 1037721 (C4 (Web Text))

Max Activating Token Index: 552

Text #10

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.5609. Min Act: -0.0001

Data Index: 1192575 (C4 (Web Text))

Max Activating Token Index: 837

Text #11

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.6076. Min Act: -0.0001

Data Index: 1184894 (C4 (Web Text))

Max Activating Token Index: 925

Text #12

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.6280. Min Act: -0.0001

Data Index: 786026 (C4 (Web Text))

Max Activating Token Index: 302

Text #13

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.6060. Min Act: -0.0001

Data Index: 1286021 (C4 (Web Text))

Max Activating Token Index: 391

Text #14

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.5657. Min Act: -0.0001

Data Index: 1268582 (C4 (Web Text))

Max Activating Token Index: 647

Text #15

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.5692. Min Act: -0.0001

Data Index: 968061 (C4 (Web Text))

Max Activating Token Index: 171

Text #16

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.6047. Min Act: -0.0001

Data Index: 759699 (C4 (Web Text))

Max Activating Token Index: 239

Text #17

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.5821. Min Act: -0.0001

Data Index: 1356539 (C4 (Web Text))

Max Activating Token Index: 500

Text #18

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.5308. Min Act: -0.0001

Data Index: 699979 (C4 (Web Text))

Max Activating Token Index: 780

Text #19

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.6325. Min Act: -0.0001

Data Index: 64305 (C4 (Web Text))

Max Activating Token Index: 118