Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1679 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6718. Min Range: -0.6718

Max Act: 0.6696. Min Act: -0.0000

Data Index: 1343193 (C4 (Web Text))

Max Activating Token Index: 311

Text #1

Max Range: 0.6718. Min Range: -0.6718

Max Act: 0.6351. Min Act: -0.0001

Data Index: 1150612 (C4 (Web Text))

Max Activating Token Index: 951

Text #2

Max Range: 0.6718. Min Range: -0.6718

Max Act: 0.6497. Min Act: -0.0001

Data Index: 659386 (C4 (Web Text))

Max Activating Token Index: 1012

Text #3

Max Range: 0.6718. Min Range: -0.6718

Max Act: 0.6718. Min Act: -0.0000

Data Index: 308764 (C4 (Web Text))

Max Activating Token Index: 585

Text #4

Max Range: 0.6718. Min Range: -0.6718

Max Act: 0.6221. Min Act: -0.0000

Data Index: 302990 (C4 (Web Text))

Max Activating Token Index: 197

Text #5

Max Range: 0.6718. Min Range: -0.6718

Max Act: 0.6263. Min Act: -0.0000

Data Index: 278811 (C4 (Web Text))

Max Activating Token Index: 824

Text #6

Max Range: 0.6718. Min Range: -0.6718

Max Act: 0.6398. Min Act: -0.0000

Data Index: 790097 (C4 (Web Text))

Max Activating Token Index: 478

Text #7

Max Range: 0.6718. Min Range: -0.6718

Max Act: 0.6415. Min Act: -0.0000

Data Index: 409989 (C4 (Web Text))

Max Activating Token Index: 394

Text #8

Max Range: 0.6718. Min Range: -0.6718

Max Act: 0.6142. Min Act: -0.0000

Data Index: 1056592 (C4 (Web Text))

Max Activating Token Index: 326

Text #9

Max Range: 0.6718. Min Range: -0.6718

Max Act: 0.6347. Min Act: -0.0001

Data Index: 818350 (C4 (Web Text))

Max Activating Token Index: 697

Text #10

Max Range: 0.6718. Min Range: -0.6718

Max Act: 0.6156. Min Act: -0.0000

Data Index: 688223 (C4 (Web Text))

Max Activating Token Index: 906

Text #11

Max Range: 0.6718. Min Range: -0.6718

Max Act: 0.5982. Min Act: -0.0000

Data Index: 1231641 (C4 (Web Text))

Max Activating Token Index: 641

Text #12

Max Range: 0.6718. Min Range: -0.6718

Max Act: 0.6128. Min Act: -0.0001

Data Index: 221480 (C4 (Web Text))

Max Activating Token Index: 472

Text #13

Max Range: 0.6718. Min Range: -0.6718

Max Act: 0.5937. Min Act: -0.0000

Data Index: 343661 (C4 (Web Text))

Max Activating Token Index: 260

Text #14

Max Range: 0.6718. Min Range: -0.6718

Max Act: 0.6040. Min Act: -0.0000

Data Index: 374326 (C4 (Web Text))

Max Activating Token Index: 725

Text #15

Max Range: 0.6718. Min Range: -0.6718

Max Act: 0.6008. Min Act: -0.0000

Data Index: 490541 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 0.6718. Min Range: -0.6718

Max Act: 0.6385. Min Act: -0.0000

Data Index: 1508697 (Python Code)

Max Activating Token Index: 353

Text #17

Max Range: 0.6718. Min Range: -0.6718

Max Act: 0.5976. Min Act: -0.0001

Data Index: 792006 (C4 (Web Text))

Max Activating Token Index: 498

Text #18

Max Range: 0.6718. Min Range: -0.6718

Max Act: 0.5945. Min Act: -0.0001

Data Index: 458255 (C4 (Web Text))

Max Activating Token Index: 187

Text #19

Max Range: 0.6718. Min Range: -0.6718

Max Act: 0.6106. Min Act: -0.0001

Data Index: 361731 (C4 (Web Text))

Max Activating Token Index: 712