Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 2021 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0600. Min Act: -0.0006

Data Index: 923264 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0561. Min Act: -0.0006

Data Index: 755556 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0524. Min Act: -0.0006

Data Index: 1191573 (C4 (Web Text))

Max Activating Token Index: 480

Text #3

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0494. Min Act: -0.0006

Data Index: 206005 (C4 (Web Text))

Max Activating Token Index: 592

Text #4

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0493. Min Act: -0.0006

Data Index: 660678 (C4 (Web Text))

Max Activating Token Index: 19

Text #5

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0477. Min Act: -0.0006

Data Index: 173764 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0494. Min Act: -0.0006

Data Index: 1169030 (C4 (Web Text))

Max Activating Token Index: 412

Text #7

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0483. Min Act: -0.0006

Data Index: 1284399 (C4 (Web Text))

Max Activating Token Index: 616

Text #8

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0512. Min Act: -0.0006

Data Index: 979765 (C4 (Web Text))

Max Activating Token Index: 652

Text #9

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0481. Min Act: -0.0006

Data Index: 1020687 (C4 (Web Text))

Max Activating Token Index: 601

Text #10

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0499. Min Act: -0.0006

Data Index: 1210225 (C4 (Web Text))

Max Activating Token Index: 30

Text #11

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0465. Min Act: -0.0006

Data Index: 801781 (C4 (Web Text))

Max Activating Token Index: 395

Text #12

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0484. Min Act: -0.0006

Data Index: 1262650 (C4 (Web Text))

Max Activating Token Index: 577

Text #13

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0465. Min Act: -0.0006

Data Index: 1236558 (C4 (Web Text))

Max Activating Token Index: 141

Text #14

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0470. Min Act: -0.0006

Data Index: 618132 (C4 (Web Text))

Max Activating Token Index: 635

Text #15

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0523. Min Act: -0.0006

Data Index: 1060732 (C4 (Web Text))

Max Activating Token Index: 580

Text #16

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0490. Min Act: -0.0006

Data Index: 388651 (C4 (Web Text))

Max Activating Token Index: 973

Text #17

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0489. Min Act: -0.0006

Data Index: 282910 (C4 (Web Text))

Max Activating Token Index: 548

Text #18

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0479. Min Act: -0.0006

Data Index: 150723 (C4 (Web Text))

Max Activating Token Index: 26

Text #19

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0483. Min Act: -0.0006

Data Index: 246011 (C4 (Web Text))

Max Activating Token Index: 914