Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3172 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9651. Min Range: -0.9651

Max Act: 0.9651. Min Act: -0.0001

Data Index: 1360031 (Python Code)

Max Activating Token Index: 600

Text #1

Max Range: 0.9651. Min Range: -0.9651

Max Act: 0.9283. Min Act: -0.0002

Data Index: 201909 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 0.9651. Min Range: -0.9651

Max Act: 0.9626. Min Act: -0.0001

Data Index: 82691 (C4 (Web Text))

Max Activating Token Index: 939

Text #3

Max Range: 0.9651. Min Range: -0.9651

Max Act: 0.8611. Min Act: -0.0001

Data Index: 1206683 (C4 (Web Text))

Max Activating Token Index: 164

Text #4

Max Range: 0.9651. Min Range: -0.9651

Max Act: 0.9032. Min Act: -0.0002

Data Index: 208232 (C4 (Web Text))

Max Activating Token Index: 961

Text #5

Max Range: 0.9651. Min Range: -0.9651

Max Act: 0.8652. Min Act: -0.0001

Data Index: 922565 (C4 (Web Text))

Max Activating Token Index: 980

Text #6

Max Range: 0.9651. Min Range: -0.9651

Max Act: 0.8035. Min Act: -0.0001

Data Index: 551244 (C4 (Web Text))

Max Activating Token Index: 816

Text #7

Max Range: 0.9651. Min Range: -0.9651

Max Act: 0.8202. Min Act: -0.0001

Data Index: 208507 (C4 (Web Text))

Max Activating Token Index: 602

Text #8

Max Range: 0.9651. Min Range: -0.9651

Max Act: 0.8140. Min Act: -0.0001

Data Index: 220809 (C4 (Web Text))

Max Activating Token Index: 48

Text #9

Max Range: 0.9651. Min Range: -0.9651

Max Act: 0.7257. Min Act: -0.0002

Data Index: 912185 (C4 (Web Text))

Max Activating Token Index: 723

Text #10

Max Range: 0.9651. Min Range: -0.9651

Max Act: 0.7693. Min Act: -0.0001

Data Index: 605214 (C4 (Web Text))

Max Activating Token Index: 617

Text #11

Max Range: 0.9651. Min Range: -0.9651

Max Act: 0.7670. Min Act: -0.0002

Data Index: 24202 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 0.9651. Min Range: -0.9651

Max Act: 0.8058. Min Act: -0.0002

Data Index: 455938 (C4 (Web Text))

Max Activating Token Index: 136

Text #13

Max Range: 0.9651. Min Range: -0.9651

Max Act: 0.7593. Min Act: -0.0001

Data Index: 71923 (C4 (Web Text))

Max Activating Token Index: 738

Text #14

Max Range: 0.9651. Min Range: -0.9651

Max Act: 0.8040. Min Act: -0.0001

Data Index: 782478 (C4 (Web Text))

Max Activating Token Index: 523

Text #15

Max Range: 0.9651. Min Range: -0.9651

Max Act: 0.7708. Min Act: -0.0001

Data Index: 1009111 (C4 (Web Text))

Max Activating Token Index: 298

Text #16

Max Range: 0.9651. Min Range: -0.9651

Max Act: 0.7716. Min Act: -0.0002

Data Index: 564749 (C4 (Web Text))

Max Activating Token Index: 36

Text #17

Max Range: 0.9651. Min Range: -0.9651

Max Act: 0.7716. Min Act: -0.0002

Data Index: 881538 (C4 (Web Text))

Max Activating Token Index: 540

Text #18

Max Range: 0.9651. Min Range: -0.9651

Max Act: 0.7918. Min Act: -0.0002

Data Index: 897325 (C4 (Web Text))

Max Activating Token Index: 168

Text #19

Max Range: 0.9651. Min Range: -0.9651

Max Act: 0.7257. Min Act: -0.0001

Data Index: 1350889 (C4 (Web Text))

Max Activating Token Index: 16