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

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

Neuron 3052 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.2653. Min Act: -0.0001

Data Index: 85617 (C4 (Web Text))

Max Activating Token Index: 196

Text #1

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.2807. Min Act: -0.0000

Data Index: 1246320 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.2338. Min Act: -0.0000

Data Index: 1071548 (C4 (Web Text))

Max Activating Token Index: 256

Text #3

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.2227. Min Act: -0.0001

Data Index: 272404 (C4 (Web Text))

Max Activating Token Index: 36

Text #4

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.2268. Min Act: -0.0000

Data Index: 1045324 (C4 (Web Text))

Max Activating Token Index: 723

Text #5

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.1991. Min Act: -0.0001

Data Index: 1166848 (C4 (Web Text))

Max Activating Token Index: 472

Text #6

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.1906. Min Act: -0.0001

Data Index: 376322 (C4 (Web Text))

Max Activating Token Index: 1016

Text #7

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.1900. Min Act: -0.0000

Data Index: 1080462 (C4 (Web Text))

Max Activating Token Index: 184

Text #8

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.1951. Min Act: -0.0000

Data Index: 974681 (C4 (Web Text))

Max Activating Token Index: 59

Text #9

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.1695. Min Act: -0.0000

Data Index: 860710 (C4 (Web Text))

Max Activating Token Index: 599

Text #10

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.1814. Min Act: -0.0001

Data Index: 886852 (C4 (Web Text))

Max Activating Token Index: 909

Text #11

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.1698. Min Act: -0.0001

Data Index: 587232 (C4 (Web Text))

Max Activating Token Index: 951

Text #12

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.1729. Min Act: -0.0001

Data Index: 1120255 (C4 (Web Text))

Max Activating Token Index: 744

Text #13

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.1780. Min Act: -0.0001

Data Index: 1180618 (C4 (Web Text))

Max Activating Token Index: 424

Text #14

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.1773. Min Act: -0.0000

Data Index: 245220 (C4 (Web Text))

Max Activating Token Index: 931

Text #15

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.1661. Min Act: -0.0001

Data Index: 469920 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.1496. Min Act: -0.0000

Data Index: 15802 (C4 (Web Text))

Max Activating Token Index: 257

Text #17

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.1689. Min Act: -0.0001

Data Index: 116375 (C4 (Web Text))

Max Activating Token Index: 570

Text #18

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.1751. Min Act: -0.0001

Data Index: 568504 (C4 (Web Text))

Max Activating Token Index: 250

Text #19

Max Range: 0.2807. Min Range: -0.2807

Max Act: 0.1676. Min Act: -0.0001

Data Index: 801465 (C4 (Web Text))

Max Activating Token Index: 713