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

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

Neuron 4134 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: 1.3674. Min Range: -1.3674

Max Act: 1.3674. Min Act: -0.0000

Data Index: 195684 (C4 (Web Text))

Max Activating Token Index: 437

Text #1

Max Range: 1.3674. Min Range: -1.3674

Max Act: 1.3332. Min Act: -0.0000

Data Index: 7614 (C4 (Web Text))

Max Activating Token Index: 496

Text #2

Max Range: 1.3674. Min Range: -1.3674

Max Act: 1.2669. Min Act: -0.0000

Data Index: 390434 (C4 (Web Text))

Max Activating Token Index: 370

Text #3

Max Range: 1.3674. Min Range: -1.3674

Max Act: 1.1895. Min Act: -0.0001

Data Index: 1101127 (C4 (Web Text))

Max Activating Token Index: 364

Text #4

Max Range: 1.3674. Min Range: -1.3674

Max Act: 1.1129. Min Act: -0.0000

Data Index: 1266270 (C4 (Web Text))

Max Activating Token Index: 796

Text #5

Max Range: 1.3674. Min Range: -1.3674

Max Act: 1.1104. Min Act: -0.0000

Data Index: 647768 (C4 (Web Text))

Max Activating Token Index: 662

Text #6

Max Range: 1.3674. Min Range: -1.3674

Max Act: 1.0238. Min Act: -0.0000

Data Index: 671150 (C4 (Web Text))

Max Activating Token Index: 328

Text #7

Max Range: 1.3674. Min Range: -1.3674

Max Act: 1.0838. Min Act: -0.0000

Data Index: 377826 (C4 (Web Text))

Max Activating Token Index: 1009

Text #8

Max Range: 1.3674. Min Range: -1.3674

Max Act: 1.0423. Min Act: -0.0000

Data Index: 568711 (C4 (Web Text))

Max Activating Token Index: 350

Text #9

Max Range: 1.3674. Min Range: -1.3674

Max Act: 1.0665. Min Act: -0.0001

Data Index: 717705 (C4 (Web Text))

Max Activating Token Index: 101

Text #10

Max Range: 1.3674. Min Range: -1.3674

Max Act: 0.9335. Min Act: -0.0000

Data Index: 50316 (C4 (Web Text))

Max Activating Token Index: 456

Text #11

Max Range: 1.3674. Min Range: -1.3674

Max Act: 0.9305. Min Act: -0.0001

Data Index: 584008 (C4 (Web Text))

Max Activating Token Index: 421

Text #12

Max Range: 1.3674. Min Range: -1.3674

Max Act: 1.0508. Min Act: -0.0001

Data Index: 1278898 (C4 (Web Text))

Max Activating Token Index: 669

Text #13

Max Range: 1.3674. Min Range: -1.3674

Max Act: 0.9873. Min Act: -0.0000

Data Index: 372184 (C4 (Web Text))

Max Activating Token Index: 414

Text #14

Max Range: 1.3674. Min Range: -1.3674

Max Act: 0.9786. Min Act: -0.0000

Data Index: 1036020 (C4 (Web Text))

Max Activating Token Index: 299

Text #15

Max Range: 1.3674. Min Range: -1.3674

Max Act: 0.9434. Min Act: -0.0000

Data Index: 950276 (C4 (Web Text))

Max Activating Token Index: 197

Text #16

Max Range: 1.3674. Min Range: -1.3674

Max Act: 0.9443. Min Act: -0.0001

Data Index: 584236 (C4 (Web Text))

Max Activating Token Index: 106

Text #17

Max Range: 1.3674. Min Range: -1.3674

Max Act: 1.0353. Min Act: -0.0000

Data Index: 704853 (C4 (Web Text))

Max Activating Token Index: 696

Text #18

Max Range: 1.3674. Min Range: -1.3674

Max Act: 0.9614. Min Act: -0.0000

Data Index: 322606 (C4 (Web Text))

Max Activating Token Index: 779

Text #19

Max Range: 1.3674. Min Range: -1.3674

Max Act: 0.9546. Min Act: -0.0000

Data Index: 225772 (C4 (Web Text))

Max Activating Token Index: 1006