Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5625 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1142. Min Range: -1.1142

Max Act: 1.0995. Min Act: -0.0000

Data Index: 1005231 (C4 (Web Text))

Max Activating Token Index: 244

Text #1

Max Range: 1.1142. Min Range: -1.1142

Max Act: 1.0641. Min Act: -0.0000

Data Index: 1233893 (C4 (Web Text))

Max Activating Token Index: 36

Text #2

Max Range: 1.1142. Min Range: -1.1142

Max Act: 1.1010. Min Act: -0.0000

Data Index: 1249937 (C4 (Web Text))

Max Activating Token Index: 352

Text #3

Max Range: 1.1142. Min Range: -1.1142

Max Act: 1.1142. Min Act: -0.0000

Data Index: 452152 (C4 (Web Text))

Max Activating Token Index: 300

Text #4

Max Range: 1.1142. Min Range: -1.1142

Max Act: 1.0176. Min Act: -0.0000

Data Index: 404262 (C4 (Web Text))

Max Activating Token Index: 923

Text #5

Max Range: 1.1142. Min Range: -1.1142

Max Act: 1.0406. Min Act: -0.0000

Data Index: 1052091 (C4 (Web Text))

Max Activating Token Index: 240

Text #6

Max Range: 1.1142. Min Range: -1.1142

Max Act: 0.9164. Min Act: -0.0000

Data Index: 897552 (C4 (Web Text))

Max Activating Token Index: 467

Text #7

Max Range: 1.1142. Min Range: -1.1142

Max Act: 0.9439. Min Act: -0.0000

Data Index: 917000 (C4 (Web Text))

Max Activating Token Index: 720

Text #8

Max Range: 1.1142. Min Range: -1.1142

Max Act: 0.9701. Min Act: -0.0000

Data Index: 1042916 (C4 (Web Text))

Max Activating Token Index: 112

Text #9

Max Range: 1.1142. Min Range: -1.1142

Max Act: 0.8578. Min Act: -0.0000

Data Index: 702679 (C4 (Web Text))

Max Activating Token Index: 675

Text #10

Max Range: 1.1142. Min Range: -1.1142

Max Act: 0.8836. Min Act: -0.0000

Data Index: 1131591 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 1.1142. Min Range: -1.1142

Max Act: 0.8837. Min Act: -0.0000

Data Index: 1123278 (C4 (Web Text))

Max Activating Token Index: 553

Text #12

Max Range: 1.1142. Min Range: -1.1142

Max Act: 0.8225. Min Act: -0.0000

Data Index: 920270 (C4 (Web Text))

Max Activating Token Index: 702

Text #13

Max Range: 1.1142. Min Range: -1.1142

Max Act: 0.8182. Min Act: -0.0000

Data Index: 385548 (C4 (Web Text))

Max Activating Token Index: 628

Text #14

Max Range: 1.1142. Min Range: -1.1142

Max Act: 0.8602. Min Act: -0.0000

Data Index: 1099164 (C4 (Web Text))

Max Activating Token Index: 59

Text #15

Max Range: 1.1142. Min Range: -1.1142

Max Act: 0.8806. Min Act: -0.0000

Data Index: 19705 (C4 (Web Text))

Max Activating Token Index: 371

Text #16

Max Range: 1.1142. Min Range: -1.1142

Max Act: 0.8466. Min Act: -0.0000

Data Index: 1347983 (C4 (Web Text))

Max Activating Token Index: 162

Text #17

Max Range: 1.1142. Min Range: -1.1142

Max Act: 0.8931. Min Act: -0.0000

Data Index: 920142 (C4 (Web Text))

Max Activating Token Index: 272

Text #18

Max Range: 1.1142. Min Range: -1.1142

Max Act: 0.8609. Min Act: -0.0000

Data Index: 230876 (C4 (Web Text))

Max Activating Token Index: 135

Text #19

Max Range: 1.1142. Min Range: -1.1142

Max Act: 0.8580. Min Act: -0.0000

Data Index: 439385 (C4 (Web Text))

Max Activating Token Index: 588