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

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

Neuron 5788 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.8247. Min Range: -6.8247

Max Act: 6.8247. Min Act: -0.0000

Data Index: 1070854 (C4 (Web Text))

Max Activating Token Index: 322

Text #1

Max Range: 6.8247. Min Range: -6.8247

Max Act: 5.7357. Min Act: -0.0001

Data Index: 146851 (C4 (Web Text))

Max Activating Token Index: 447

Text #2

Max Range: 6.8247. Min Range: -6.8247

Max Act: 5.9602. Min Act: -0.0000

Data Index: 535368 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 6.8247. Min Range: -6.8247

Max Act: 4.7032. Min Act: -0.0001

Data Index: 943252 (C4 (Web Text))

Max Activating Token Index: 305

Text #4

Max Range: 6.8247. Min Range: -6.8247

Max Act: 4.8665. Min Act: -0.0000

Data Index: 1155724 (C4 (Web Text))

Max Activating Token Index: 521

Text #5

Max Range: 6.8247. Min Range: -6.8247

Max Act: 4.6987. Min Act: -0.0000

Data Index: 536387 (C4 (Web Text))

Max Activating Token Index: 306

Text #6

Max Range: 6.8247. Min Range: -6.8247

Max Act: 4.5453. Min Act: -0.0000

Data Index: 699719 (C4 (Web Text))

Max Activating Token Index: 350

Text #7

Max Range: 6.8247. Min Range: -6.8247

Max Act: 4.5040. Min Act: -0.0001

Data Index: 183512 (C4 (Web Text))

Max Activating Token Index: 169

Text #8

Max Range: 6.8247. Min Range: -6.8247

Max Act: 4.2966. Min Act: -0.0000

Data Index: 1338666 (C4 (Web Text))

Max Activating Token Index: 627

Text #9

Max Range: 6.8247. Min Range: -6.8247

Max Act: 4.2750. Min Act: -0.0001

Data Index: 557834 (C4 (Web Text))

Max Activating Token Index: 164

Text #10

Max Range: 6.8247. Min Range: -6.8247

Max Act: 4.1542. Min Act: -0.0001

Data Index: 152853 (C4 (Web Text))

Max Activating Token Index: 804

Text #11

Max Range: 6.8247. Min Range: -6.8247

Max Act: 4.4044. Min Act: -0.0001

Data Index: 1329971 (C4 (Web Text))

Max Activating Token Index: 1010

Text #12

Max Range: 6.8247. Min Range: -6.8247

Max Act: 4.0685. Min Act: -0.0000

Data Index: 1023033 (C4 (Web Text))

Max Activating Token Index: 799

Text #13

Max Range: 6.8247. Min Range: -6.8247

Max Act: 3.9675. Min Act: -0.0000

Data Index: 139552 (C4 (Web Text))

Max Activating Token Index: 62

Text #14

Max Range: 6.8247. Min Range: -6.8247

Max Act: 4.0977. Min Act: -0.0001

Data Index: 1344778 (C4 (Web Text))

Max Activating Token Index: 97

Text #15

Max Range: 6.8247. Min Range: -6.8247

Max Act: 4.1039. Min Act: -0.0001

Data Index: 263668 (C4 (Web Text))

Max Activating Token Index: 717

Text #16

Max Range: 6.8247. Min Range: -6.8247

Max Act: 3.9600. Min Act: -0.0001

Data Index: 575175 (C4 (Web Text))

Max Activating Token Index: 538

Text #17

Max Range: 6.8247. Min Range: -6.8247

Max Act: 3.8045. Min Act: -0.0001

Data Index: 664580 (C4 (Web Text))

Max Activating Token Index: 87

Text #18

Max Range: 6.8247. Min Range: -6.8247

Max Act: 3.7674. Min Act: -0.0001

Data Index: 381905 (C4 (Web Text))

Max Activating Token Index: 907

Text #19

Max Range: 6.8247. Min Range: -6.8247

Max Act: 4.0781. Min Act: -0.0001

Data Index: 1017164 (C4 (Web Text))

Max Activating Token Index: 466