Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1217 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0635. Min Act: -0.0002

Data Index: 1314816 (C4 (Web Text))

Max Activating Token Index: 1008

Text #1

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0670. Min Act: -0.0002

Data Index: 951955 (C4 (Web Text))

Max Activating Token Index: 178

Text #2

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0592. Min Act: -0.0002

Data Index: 233078 (C4 (Web Text))

Max Activating Token Index: 911

Text #3

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0588. Min Act: -0.0002

Data Index: 564831 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0644. Min Act: -0.0002

Data Index: 356981 (C4 (Web Text))

Max Activating Token Index: 237

Text #5

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0610. Min Act: -0.0002

Data Index: 488477 (C4 (Web Text))

Max Activating Token Index: 984

Text #6

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0628. Min Act: -0.0002

Data Index: 836154 (C4 (Web Text))

Max Activating Token Index: 383

Text #7

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0487. Min Act: -0.0002

Data Index: 104621 (C4 (Web Text))

Max Activating Token Index: 151

Text #8

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0563. Min Act: -0.0002

Data Index: 1557710 (Python Code)

Max Activating Token Index: 736

Text #9

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0565. Min Act: -0.0002

Data Index: 1179918 (C4 (Web Text))

Max Activating Token Index: 487

Text #10

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0504. Min Act: -0.0002

Data Index: 1558279 (Python Code)

Max Activating Token Index: 903

Text #11

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0581. Min Act: -0.0002

Data Index: 782862 (C4 (Web Text))

Max Activating Token Index: 430

Text #12

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0554. Min Act: -0.0002

Data Index: 364305 (C4 (Web Text))

Max Activating Token Index: 56

Text #13

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0475. Min Act: -0.0002

Data Index: 1242715 (C4 (Web Text))

Max Activating Token Index: 207

Text #14

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0548. Min Act: -0.0002

Data Index: 762614 (C4 (Web Text))

Max Activating Token Index: 7

Text #15

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0545. Min Act: -0.0002

Data Index: 1980 (C4 (Web Text))

Max Activating Token Index: 4

Text #16

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0530. Min Act: -0.0002

Data Index: 418543 (C4 (Web Text))

Max Activating Token Index: 152

Text #17

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0594. Min Act: -0.0002

Data Index: 1074475 (C4 (Web Text))

Max Activating Token Index: 723

Text #18

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0442. Min Act: -0.0002

Data Index: 1393729 (Python Code)

Max Activating Token Index: 725

Text #19

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0509. Min Act: -0.0002

Data Index: 1290579 (C4 (Web Text))

Max Activating Token Index: 497