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

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

Neuron 1231 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9478. Min Range: -0.9478

Max Act: 0.9478. Min Act: -0.0000

Data Index: 1274145 (C4 (Web Text))

Max Activating Token Index: 309

Text #1

Max Range: 0.9478. Min Range: -0.9478

Max Act: 0.8745. Min Act: -0.0000

Data Index: 34558 (C4 (Web Text))

Max Activating Token Index: 251

Text #2

Max Range: 0.9478. Min Range: -0.9478

Max Act: 0.9179. Min Act: -0.0000

Data Index: 1573677 (Python Code)

Max Activating Token Index: 819

Text #3

Max Range: 0.9478. Min Range: -0.9478

Max Act: 0.8689. Min Act: -0.0000

Data Index: 552735 (C4 (Web Text))

Max Activating Token Index: 46

Text #4

Max Range: 0.9478. Min Range: -0.9478

Max Act: 0.8567. Min Act: -0.0000

Data Index: 857608 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 0.9478. Min Range: -0.9478

Max Act: 0.8500. Min Act: -0.0000

Data Index: 832461 (C4 (Web Text))

Max Activating Token Index: 691

Text #6

Max Range: 0.9478. Min Range: -0.9478

Max Act: 0.8490. Min Act: -0.0000

Data Index: 626861 (C4 (Web Text))

Max Activating Token Index: 434

Text #7

Max Range: 0.9478. Min Range: -0.9478

Max Act: 0.8360. Min Act: -0.0000

Data Index: 833658 (C4 (Web Text))

Max Activating Token Index: 31

Text #8

Max Range: 0.9478. Min Range: -0.9478

Max Act: 0.8920. Min Act: -0.0000

Data Index: 599167 (C4 (Web Text))

Max Activating Token Index: 826

Text #9

Max Range: 0.9478. Min Range: -0.9478

Max Act: 0.8154. Min Act: -0.0000

Data Index: 1359520 (C4 (Web Text))

Max Activating Token Index: 811

Text #10

Max Range: 0.9478. Min Range: -0.9478

Max Act: 0.8334. Min Act: -0.0000

Data Index: 1650211 (Python Code)

Max Activating Token Index: 223

Text #11

Max Range: 0.9478. Min Range: -0.9478

Max Act: 0.7899. Min Act: -0.0000

Data Index: 814587 (C4 (Web Text))

Max Activating Token Index: 183

Text #12

Max Range: 0.9478. Min Range: -0.9478

Max Act: 0.7360. Min Act: 0.0000

Data Index: 301296 (C4 (Web Text))

Max Activating Token Index: 927

Text #13

Max Range: 0.9478. Min Range: -0.9478

Max Act: 0.8111. Min Act: -0.0000

Data Index: 1006412 (C4 (Web Text))

Max Activating Token Index: 19

Text #14

Max Range: 0.9478. Min Range: -0.9478

Max Act: 0.7798. Min Act: -0.0000

Data Index: 1179655 (C4 (Web Text))

Max Activating Token Index: 342

Text #15

Max Range: 0.9478. Min Range: -0.9478

Max Act: 0.7952. Min Act: -0.0000

Data Index: 34739 (C4 (Web Text))

Max Activating Token Index: 493

Text #16

Max Range: 0.9478. Min Range: -0.9478

Max Act: 0.7664. Min Act: -0.0000

Data Index: 231712 (C4 (Web Text))

Max Activating Token Index: 751

Text #17

Max Range: 0.9478. Min Range: -0.9478

Max Act: 0.7509. Min Act: -0.0000

Data Index: 1416479 (Python Code)

Max Activating Token Index: 978

Text #18

Max Range: 0.9478. Min Range: -0.9478

Max Act: 0.7451. Min Act: -0.0000

Data Index: 539999 (C4 (Web Text))

Max Activating Token Index: 654

Text #19

Max Range: 0.9478. Min Range: -0.9478

Max Act: 0.7633. Min Act: -0.0000

Data Index: 694100 (C4 (Web Text))

Max Activating Token Index: 532