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

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

Neuron 882 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: 1.0572. Min Range: -1.0572

Max Act: 1.0572. Min Act: -0.0000

Data Index: 534592 (C4 (Web Text))

Max Activating Token Index: 240

Text #1

Max Range: 1.0572. Min Range: -1.0572

Max Act: 0.9654. Min Act: -0.0001

Data Index: 126418 (C4 (Web Text))

Max Activating Token Index: 536

Text #2

Max Range: 1.0572. Min Range: -1.0572

Max Act: 1.0328. Min Act: -0.0000

Data Index: 1007835 (C4 (Web Text))

Max Activating Token Index: 849

Text #3

Max Range: 1.0572. Min Range: -1.0572

Max Act: 0.9652. Min Act: -0.0001

Data Index: 1011424 (C4 (Web Text))

Max Activating Token Index: 464

Text #4

Max Range: 1.0572. Min Range: -1.0572

Max Act: 0.9854. Min Act: -0.0000

Data Index: 479054 (C4 (Web Text))

Max Activating Token Index: 153

Text #5

Max Range: 1.0572. Min Range: -1.0572

Max Act: 0.9520. Min Act: -0.0000

Data Index: 341640 (C4 (Web Text))

Max Activating Token Index: 809

Text #6

Max Range: 1.0572. Min Range: -1.0572

Max Act: 0.9142. Min Act: -0.0000

Data Index: 241454 (C4 (Web Text))

Max Activating Token Index: 1009

Text #7

Max Range: 1.0572. Min Range: -1.0572

Max Act: 0.9200. Min Act: -0.0000

Data Index: 857141 (C4 (Web Text))

Max Activating Token Index: 500

Text #8

Max Range: 1.0572. Min Range: -1.0572

Max Act: 0.9187. Min Act: -0.0000

Data Index: 405247 (C4 (Web Text))

Max Activating Token Index: 238

Text #9

Max Range: 1.0572. Min Range: -1.0572

Max Act: 0.8826. Min Act: -0.0000

Data Index: 1190519 (C4 (Web Text))

Max Activating Token Index: 517

Text #10

Max Range: 1.0572. Min Range: -1.0572

Max Act: 0.8824. Min Act: -0.0001

Data Index: 751096 (C4 (Web Text))

Max Activating Token Index: 90

Text #11

Max Range: 1.0572. Min Range: -1.0572

Max Act: 0.8809. Min Act: -0.0001

Data Index: 1034721 (C4 (Web Text))

Max Activating Token Index: 584

Text #12

Max Range: 1.0572. Min Range: -1.0572

Max Act: 0.8610. Min Act: -0.0001

Data Index: 608215 (C4 (Web Text))

Max Activating Token Index: 595

Text #13

Max Range: 1.0572. Min Range: -1.0572

Max Act: 0.8097. Min Act: -0.0000

Data Index: 1136659 (C4 (Web Text))

Max Activating Token Index: 969

Text #14

Max Range: 1.0572. Min Range: -1.0572

Max Act: 0.8357. Min Act: -0.0000

Data Index: 214425 (C4 (Web Text))

Max Activating Token Index: 861

Text #15

Max Range: 1.0572. Min Range: -1.0572

Max Act: 0.8245. Min Act: -0.0000

Data Index: 36961 (C4 (Web Text))

Max Activating Token Index: 833

Text #16

Max Range: 1.0572. Min Range: -1.0572

Max Act: 0.8062. Min Act: -0.0000

Data Index: 1147066 (C4 (Web Text))

Max Activating Token Index: 863

Text #17

Max Range: 1.0572. Min Range: -1.0572

Max Act: 0.7690. Min Act: -0.0000

Data Index: 55682 (C4 (Web Text))

Max Activating Token Index: 305

Text #18

Max Range: 1.0572. Min Range: -1.0572

Max Act: 0.7988. Min Act: -0.0000

Data Index: 264397 (C4 (Web Text))

Max Activating Token Index: 247

Text #19

Max Range: 1.0572. Min Range: -1.0572

Max Act: 0.8036. Min Act: -0.0001

Data Index: 274481 (C4 (Web Text))

Max Activating Token Index: 847