Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1562 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0663. Min Act: -0.0003

Data Index: 925256 (C4 (Web Text))

Max Activating Token Index: 602

Text #1

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0642. Min Act: -0.0003

Data Index: 1332564 (C4 (Web Text))

Max Activating Token Index: 215

Text #2

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0656. Min Act: -0.0003

Data Index: 580202 (C4 (Web Text))

Max Activating Token Index: 593

Text #3

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0676. Min Act: -0.0003

Data Index: 1251872 (C4 (Web Text))

Max Activating Token Index: 92

Text #4

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0717. Min Act: -0.0003

Data Index: 87 (C4 (Web Text))

Max Activating Token Index: 701

Text #5

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0662. Min Act: -0.0003

Data Index: 170512 (C4 (Web Text))

Max Activating Token Index: 58

Text #6

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0716. Min Act: -0.0003

Data Index: 1170588 (C4 (Web Text))

Max Activating Token Index: 306

Text #7

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0650. Min Act: -0.0003

Data Index: 116072 (C4 (Web Text))

Max Activating Token Index: 917

Text #8

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0676. Min Act: -0.0003

Data Index: 616591 (C4 (Web Text))

Max Activating Token Index: 92

Text #9

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0621. Min Act: -0.0003

Data Index: 330529 (C4 (Web Text))

Max Activating Token Index: 852

Text #10

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0623. Min Act: -0.0003

Data Index: 990458 (C4 (Web Text))

Max Activating Token Index: 68

Text #11

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0660. Min Act: -0.0003

Data Index: 871120 (C4 (Web Text))

Max Activating Token Index: 925

Text #12

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0599. Min Act: -0.0003

Data Index: 1282318 (C4 (Web Text))

Max Activating Token Index: 178

Text #13

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0589. Min Act: -0.0003

Data Index: 591524 (C4 (Web Text))

Max Activating Token Index: 44

Text #14

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0566. Min Act: -0.0003

Data Index: 1138126 (C4 (Web Text))

Max Activating Token Index: 606

Text #15

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0594. Min Act: -0.0003

Data Index: 1190281 (C4 (Web Text))

Max Activating Token Index: 937

Text #16

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0590. Min Act: -0.0003

Data Index: 1023157 (C4 (Web Text))

Max Activating Token Index: 207

Text #17

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0559. Min Act: -0.0003

Data Index: 1297508 (C4 (Web Text))

Max Activating Token Index: 228

Text #18

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0473. Min Act: -0.0003

Data Index: 812815 (C4 (Web Text))

Max Activating Token Index: 859

Text #19

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0561. Min Act: -0.0003

Data Index: 631813 (C4 (Web Text))

Max Activating Token Index: 63