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

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

Neuron 2802 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: 0.1631. Min Range: -0.1631

Max Act: 0.1631. Min Act: -0.0002

Data Index: 1137349 (C4 (Web Text))

Max Activating Token Index: 142

Text #1

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1438. Min Act: -0.0001

Data Index: 1070749 (C4 (Web Text))

Max Activating Token Index: 182

Text #2

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1149. Min Act: -0.0001

Data Index: 388220 (C4 (Web Text))

Max Activating Token Index: 214

Text #3

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1124. Min Act: -0.0001

Data Index: 1304920 (C4 (Web Text))

Max Activating Token Index: 185

Text #4

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1065. Min Act: -0.0001

Data Index: 619669 (C4 (Web Text))

Max Activating Token Index: 670

Text #5

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1075. Min Act: -0.0001

Data Index: 497194 (C4 (Web Text))

Max Activating Token Index: 373

Text #6

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.0975. Min Act: -0.0001

Data Index: 642931 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.0982. Min Act: -0.0002

Data Index: 263387 (C4 (Web Text))

Max Activating Token Index: 248

Text #8

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1041. Min Act: -0.0001

Data Index: 160600 (C4 (Web Text))

Max Activating Token Index: 32

Text #9

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1012. Min Act: -0.0001

Data Index: 726411 (C4 (Web Text))

Max Activating Token Index: 236

Text #10

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.0996. Min Act: -0.0001

Data Index: 233675 (C4 (Web Text))

Max Activating Token Index: 201

Text #11

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.0923. Min Act: -0.0001

Data Index: 1065103 (C4 (Web Text))

Max Activating Token Index: 845

Text #12

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.0931. Min Act: -0.0001

Data Index: 735677 (C4 (Web Text))

Max Activating Token Index: 822

Text #13

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.0923. Min Act: -0.0001

Data Index: 1125796 (C4 (Web Text))

Max Activating Token Index: 753

Text #14

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.0991. Min Act: -0.0001

Data Index: 1216511 (C4 (Web Text))

Max Activating Token Index: 12

Text #15

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.0952. Min Act: -0.0001

Data Index: 1043934 (C4 (Web Text))

Max Activating Token Index: 1002

Text #16

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.0976. Min Act: -0.0001

Data Index: 211091 (C4 (Web Text))

Max Activating Token Index: 140

Text #17

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.0910. Min Act: -0.0001

Data Index: 106390 (C4 (Web Text))

Max Activating Token Index: 443

Text #18

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.0974. Min Act: -0.0002

Data Index: 1154462 (C4 (Web Text))

Max Activating Token Index: 506

Text #19

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.0919. Min Act: -0.0002

Data Index: 983619 (C4 (Web Text))

Max Activating Token Index: 677