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

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

Neuron 1134 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0990. Min Act: -0.0002

Data Index: 888575 (C4 (Web Text))

Max Activating Token Index: 757

Text #1

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0732. Min Act: -0.0002

Data Index: 1231358 (C4 (Web Text))

Max Activating Token Index: 338

Text #2

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0659. Min Act: -0.0002

Data Index: 479822 (C4 (Web Text))

Max Activating Token Index: 891

Text #3

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0574. Min Act: -0.0002

Data Index: 893900 (C4 (Web Text))

Max Activating Token Index: 248

Text #4

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0566. Min Act: -0.0002

Data Index: 573599 (C4 (Web Text))

Max Activating Token Index: 641

Text #5

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0536. Min Act: -0.0002

Data Index: 728188 (C4 (Web Text))

Max Activating Token Index: 845

Text #6

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0538. Min Act: -0.0002

Data Index: 317116 (C4 (Web Text))

Max Activating Token Index: 322

Text #7

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0526. Min Act: -0.0002

Data Index: 868916 (C4 (Web Text))

Max Activating Token Index: 15

Text #8

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0512. Min Act: -0.0002

Data Index: 1281453 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0509. Min Act: -0.0002

Data Index: 1308278 (C4 (Web Text))

Max Activating Token Index: 68

Text #10

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0496. Min Act: -0.0002

Data Index: 10753 (C4 (Web Text))

Max Activating Token Index: 8

Text #11

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0513. Min Act: -0.0002

Data Index: 497049 (C4 (Web Text))

Max Activating Token Index: 915

Text #12

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0495. Min Act: -0.0002

Data Index: 130019 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0499. Min Act: -0.0002

Data Index: 1216054 (C4 (Web Text))

Max Activating Token Index: 737

Text #14

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0488. Min Act: -0.0002

Data Index: 686655 (C4 (Web Text))

Max Activating Token Index: 158

Text #15

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0498. Min Act: -0.0002

Data Index: 1072799 (C4 (Web Text))

Max Activating Token Index: 79

Text #16

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0486. Min Act: -0.0002

Data Index: 1559722 (Python Code)

Max Activating Token Index: 570

Text #17

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0485. Min Act: -0.0002

Data Index: 77278 (C4 (Web Text))

Max Activating Token Index: 341

Text #18

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0468. Min Act: -0.0002

Data Index: 1091623 (C4 (Web Text))

Max Activating Token Index: 10

Text #19

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0477. Min Act: -0.0002

Data Index: 580893 (C4 (Web Text))

Max Activating Token Index: 801