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

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

Neuron 2035 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0779. Min Act: -0.0003

Data Index: 1153645 (C4 (Web Text))

Max Activating Token Index: 645

Text #1

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0758. Min Act: -0.0003

Data Index: 1332732 (C4 (Web Text))

Max Activating Token Index: 254

Text #2

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0706. Min Act: -0.0003

Data Index: 607487 (C4 (Web Text))

Max Activating Token Index: 203

Text #3

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0713. Min Act: -0.0003

Data Index: 307288 (C4 (Web Text))

Max Activating Token Index: 963

Text #4

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0668. Min Act: -0.0003

Data Index: 1112955 (C4 (Web Text))

Max Activating Token Index: 326

Text #5

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0638. Min Act: -0.0003

Data Index: 571714 (C4 (Web Text))

Max Activating Token Index: 509

Text #6

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0647. Min Act: -0.0003

Data Index: 898746 (C4 (Web Text))

Max Activating Token Index: 857

Text #7

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0639. Min Act: -0.0003

Data Index: 1012041 (C4 (Web Text))

Max Activating Token Index: 998

Text #8

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0609. Min Act: -0.0003

Data Index: 934039 (C4 (Web Text))

Max Activating Token Index: 962

Text #9

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0562. Min Act: -0.0003

Data Index: 113508 (C4 (Web Text))

Max Activating Token Index: 510

Text #10

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0557. Min Act: -0.0003

Data Index: 938304 (C4 (Web Text))

Max Activating Token Index: 58

Text #11

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0541. Min Act: -0.0002

Data Index: 131070 (C4 (Web Text))

Max Activating Token Index: 766

Text #12

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0540. Min Act: -0.0003

Data Index: 1327959 (C4 (Web Text))

Max Activating Token Index: 467

Text #13

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0500. Min Act: -0.0003

Data Index: 333297 (C4 (Web Text))

Max Activating Token Index: 124

Text #14

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0500. Min Act: -0.0003

Data Index: 1052698 (C4 (Web Text))

Max Activating Token Index: 404

Text #15

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0501. Min Act: -0.0003

Data Index: 163340 (C4 (Web Text))

Max Activating Token Index: 1009

Text #16

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0498. Min Act: -0.0002

Data Index: 1017852 (C4 (Web Text))

Max Activating Token Index: 277

Text #17

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0528. Min Act: -0.0002

Data Index: 1234567 (C4 (Web Text))

Max Activating Token Index: 614

Text #18

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0494. Min Act: -0.0003

Data Index: 754926 (C4 (Web Text))

Max Activating Token Index: 997

Text #19

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0489. Min Act: -0.0003

Data Index: 1162733 (C4 (Web Text))

Max Activating Token Index: 988