Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4067 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5659. Min Range: -0.5659

Max Act: 0.5659. Min Act: -0.0000

Data Index: 395780 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 0.5659. Min Range: -0.5659

Max Act: 0.5586. Min Act: -0.0001

Data Index: 1358695 (C4 (Web Text))

Max Activating Token Index: 580

Text #2

Max Range: 0.5659. Min Range: -0.5659

Max Act: 0.5370. Min Act: -0.0001

Data Index: 1055146 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 0.5659. Min Range: -0.5659

Max Act: 0.5367. Min Act: -0.0000

Data Index: 1061695 (C4 (Web Text))

Max Activating Token Index: 57

Text #4

Max Range: 0.5659. Min Range: -0.5659

Max Act: 0.5133. Min Act: -0.0000

Data Index: 1116111 (C4 (Web Text))

Max Activating Token Index: 353

Text #5

Max Range: 0.5659. Min Range: -0.5659

Max Act: 0.4846. Min Act: -0.0001

Data Index: 1039668 (C4 (Web Text))

Max Activating Token Index: 777

Text #6

Max Range: 0.5659. Min Range: -0.5659

Max Act: 0.4642. Min Act: -0.0001

Data Index: 1128316 (C4 (Web Text))

Max Activating Token Index: 818

Text #7

Max Range: 0.5659. Min Range: -0.5659

Max Act: 0.4504. Min Act: -0.0000

Data Index: 923864 (C4 (Web Text))

Max Activating Token Index: 700

Text #8

Max Range: 0.5659. Min Range: -0.5659

Max Act: 0.4928. Min Act: -0.0001

Data Index: 112449 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 0.5659. Min Range: -0.5659

Max Act: 0.4474. Min Act: -0.0001

Data Index: 1099868 (C4 (Web Text))

Max Activating Token Index: 840

Text #10

Max Range: 0.5659. Min Range: -0.5659

Max Act: 0.4473. Min Act: -0.0001

Data Index: 46530 (C4 (Web Text))

Max Activating Token Index: 973

Text #11

Max Range: 0.5659. Min Range: -0.5659

Max Act: 0.4626. Min Act: -0.0000

Data Index: 111108 (C4 (Web Text))

Max Activating Token Index: 877

Text #12

Max Range: 0.5659. Min Range: -0.5659

Max Act: 0.4453. Min Act: -0.0000

Data Index: 712107 (C4 (Web Text))

Max Activating Token Index: 247

Text #13

Max Range: 0.5659. Min Range: -0.5659

Max Act: 0.4435. Min Act: -0.0000

Data Index: 635868 (C4 (Web Text))

Max Activating Token Index: 253

Text #14

Max Range: 0.5659. Min Range: -0.5659

Max Act: 0.4423. Min Act: -0.0000

Data Index: 1002577 (C4 (Web Text))

Max Activating Token Index: 525

Text #15

Max Range: 0.5659. Min Range: -0.5659

Max Act: 0.4576. Min Act: -0.0000

Data Index: 621992 (C4 (Web Text))

Max Activating Token Index: 238

Text #16

Max Range: 0.5659. Min Range: -0.5659

Max Act: 0.4359. Min Act: -0.0000

Data Index: 1305753 (C4 (Web Text))

Max Activating Token Index: 850

Text #17

Max Range: 0.5659. Min Range: -0.5659

Max Act: 0.4447. Min Act: -0.0000

Data Index: 629545 (C4 (Web Text))

Max Activating Token Index: 527

Text #18

Max Range: 0.5659. Min Range: -0.5659

Max Act: 0.4453. Min Act: -0.0000

Data Index: 1212244 (C4 (Web Text))

Max Activating Token Index: 191

Text #19

Max Range: 0.5659. Min Range: -0.5659

Max Act: 0.4463. Min Act: -0.0000

Data Index: 763452 (C4 (Web Text))

Max Activating Token Index: 311