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

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

Neuron 2019 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.0045. Min Act: -0.0001

Data Index: 915959 (C4 (Web Text))

Max Activating Token Index: 456

Text #1

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1127. Min Act: -0.0001

Data Index: 783404 (C4 (Web Text))

Max Activating Token Index: 572

Text #2

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.0043. Min Act: -0.0000

Data Index: 1335442 (C4 (Web Text))

Max Activating Token Index: 176

Text #3

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1130. Min Act: -0.0000

Data Index: 1320837 (C4 (Web Text))

Max Activating Token Index: 983

Text #4

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1294. Min Act: -0.0000

Data Index: 843298 (C4 (Web Text))

Max Activating Token Index: 696

Text #5

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.0088. Min Act: -0.0001

Data Index: 915484 (C4 (Web Text))

Max Activating Token Index: 321

Text #6

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.0989. Min Act: -0.0001

Data Index: 478839 (C4 (Web Text))

Max Activating Token Index: 707

Text #7

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.0859. Min Act: -0.0000

Data Index: 1226569 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.0732. Min Act: -0.0000

Data Index: 616230 (C4 (Web Text))

Max Activating Token Index: 887

Text #9

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.0747. Min Act: -0.0000

Data Index: 1110656 (C4 (Web Text))

Max Activating Token Index: 350

Text #10

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.0710. Min Act: -0.0000

Data Index: 429193 (C4 (Web Text))

Max Activating Token Index: 348

Text #11

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.0812. Min Act: -0.0001

Data Index: 1098043 (C4 (Web Text))

Max Activating Token Index: 489

Text #12

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.0702. Min Act: -0.0000

Data Index: 1274665 (C4 (Web Text))

Max Activating Token Index: 425

Text #13

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.0645. Min Act: -0.0001

Data Index: 652645 (C4 (Web Text))

Max Activating Token Index: 990

Text #14

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.0636. Min Act: -0.0001

Data Index: 360663 (C4 (Web Text))

Max Activating Token Index: 226

Text #15

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.0576. Min Act: -0.0001

Data Index: 551676 (C4 (Web Text))

Max Activating Token Index: 929

Text #16

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.0629. Min Act: -0.0001

Data Index: 694896 (C4 (Web Text))

Max Activating Token Index: 689

Text #17

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.0581. Min Act: -0.0001

Data Index: 1136581 (C4 (Web Text))

Max Activating Token Index: 1008

Text #18

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.0616. Min Act: -0.0001

Data Index: 1160863 (C4 (Web Text))

Max Activating Token Index: 694

Text #19

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.0636. Min Act: -0.0001

Data Index: 10182 (C4 (Web Text))

Max Activating Token Index: 718