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

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

Neuron 4032 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: 0.7127. Min Range: -0.7127

Max Act: 0.7127. Min Act: -0.0001

Data Index: 318538 (C4 (Web Text))

Max Activating Token Index: 391

Text #1

Max Range: 0.7127. Min Range: -0.7127

Max Act: 0.6923. Min Act: -0.0001

Data Index: 890676 (C4 (Web Text))

Max Activating Token Index: 811

Text #2

Max Range: 0.7127. Min Range: -0.7127

Max Act: 0.6369. Min Act: -0.0001

Data Index: 675996 (C4 (Web Text))

Max Activating Token Index: 103

Text #3

Max Range: 0.7127. Min Range: -0.7127

Max Act: 0.7003. Min Act: -0.0001

Data Index: 1216475 (C4 (Web Text))

Max Activating Token Index: 986

Text #4

Max Range: 0.7127. Min Range: -0.7127

Max Act: 0.6167. Min Act: -0.0001

Data Index: 759384 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 0.7127. Min Range: -0.7127

Max Act: 0.6059. Min Act: -0.0001

Data Index: 714149 (C4 (Web Text))

Max Activating Token Index: 161

Text #6

Max Range: 0.7127. Min Range: -0.7127

Max Act: 0.6298. Min Act: -0.0001

Data Index: 1015638 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 0.7127. Min Range: -0.7127

Max Act: 0.6023. Min Act: -0.0001

Data Index: 24687 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 0.7127. Min Range: -0.7127

Max Act: 0.6633. Min Act: -0.0001

Data Index: 539655 (C4 (Web Text))

Max Activating Token Index: 19

Text #9

Max Range: 0.7127. Min Range: -0.7127

Max Act: 0.6421. Min Act: -0.0001

Data Index: 1126785 (C4 (Web Text))

Max Activating Token Index: 110

Text #10

Max Range: 0.7127. Min Range: -0.7127

Max Act: 0.6422. Min Act: -0.0001

Data Index: 204573 (C4 (Web Text))

Max Activating Token Index: 543

Text #11

Max Range: 0.7127. Min Range: -0.7127

Max Act: 0.5727. Min Act: -0.0001

Data Index: 261558 (C4 (Web Text))

Max Activating Token Index: 66

Text #12

Max Range: 0.7127. Min Range: -0.7127

Max Act: 0.6434. Min Act: -0.0001

Data Index: 1225425 (C4 (Web Text))

Max Activating Token Index: 962

Text #13

Max Range: 0.7127. Min Range: -0.7127

Max Act: 0.6546. Min Act: -0.0001

Data Index: 794936 (C4 (Web Text))

Max Activating Token Index: 247

Text #14

Max Range: 0.7127. Min Range: -0.7127

Max Act: 0.6686. Min Act: -0.0001

Data Index: 38851 (C4 (Web Text))

Max Activating Token Index: 971

Text #15

Max Range: 0.7127. Min Range: -0.7127

Max Act: 0.6423. Min Act: -0.0001

Data Index: 2143 (C4 (Web Text))

Max Activating Token Index: 21

Text #16

Max Range: 0.7127. Min Range: -0.7127

Max Act: 0.5658. Min Act: -0.0001

Data Index: 1226376 (C4 (Web Text))

Max Activating Token Index: 143

Text #17

Max Range: 0.7127. Min Range: -0.7127

Max Act: 0.5811. Min Act: -0.0001

Data Index: 551981 (C4 (Web Text))

Max Activating Token Index: 148

Text #18

Max Range: 0.7127. Min Range: -0.7127

Max Act: 0.6265. Min Act: -0.0001

Data Index: 26984 (C4 (Web Text))

Max Activating Token Index: 1005

Text #19

Max Range: 0.7127. Min Range: -0.7127

Max Act: 0.5970. Min Act: -0.0001

Data Index: 1315123 (C4 (Web Text))

Max Activating Token Index: 893