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

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

Neuron 5584 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0122. Min Range: -2.0122

Max Act: 2.0122. Min Act: -0.0000

Data Index: 86508 (C4 (Web Text))

Max Activating Token Index: 670

Text #1

Max Range: 2.0122. Min Range: -2.0122

Max Act: 1.9049. Min Act: -0.0000

Data Index: 1293321 (C4 (Web Text))

Max Activating Token Index: 262

Text #2

Max Range: 2.0122. Min Range: -2.0122

Max Act: 1.8505. Min Act: -0.0000

Data Index: 659550 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 2.0122. Min Range: -2.0122

Max Act: 1.5625. Min Act: -0.0000

Data Index: 77978 (C4 (Web Text))

Max Activating Token Index: 353

Text #4

Max Range: 2.0122. Min Range: -2.0122

Max Act: 1.5549. Min Act: -0.0000

Data Index: 2055 (C4 (Web Text))

Max Activating Token Index: 693

Text #5

Max Range: 2.0122. Min Range: -2.0122

Max Act: 1.4915. Min Act: -0.0000

Data Index: 392599 (C4 (Web Text))

Max Activating Token Index: 664

Text #6

Max Range: 2.0122. Min Range: -2.0122

Max Act: 1.4548. Min Act: -0.0000

Data Index: 1599 (C4 (Web Text))

Max Activating Token Index: 99

Text #7

Max Range: 2.0122. Min Range: -2.0122

Max Act: 1.3505. Min Act: -0.0000

Data Index: 229236 (C4 (Web Text))

Max Activating Token Index: 610

Text #8

Max Range: 2.0122. Min Range: -2.0122

Max Act: 1.3582. Min Act: -0.0000

Data Index: 1346409 (C4 (Web Text))

Max Activating Token Index: 452

Text #9

Max Range: 2.0122. Min Range: -2.0122

Max Act: 1.3520. Min Act: -0.0000

Data Index: 70877 (C4 (Web Text))

Max Activating Token Index: 111

Text #10

Max Range: 2.0122. Min Range: -2.0122

Max Act: 1.4075. Min Act: -0.0000

Data Index: 829690 (C4 (Web Text))

Max Activating Token Index: 893

Text #11

Max Range: 2.0122. Min Range: -2.0122

Max Act: 1.4108. Min Act: -0.0000

Data Index: 1049815 (C4 (Web Text))

Max Activating Token Index: 490

Text #12

Max Range: 2.0122. Min Range: -2.0122

Max Act: 1.3207. Min Act: -0.0000

Data Index: 1184073 (C4 (Web Text))

Max Activating Token Index: 310

Text #13

Max Range: 2.0122. Min Range: -2.0122

Max Act: 1.2267. Min Act: -0.0000

Data Index: 1120151 (C4 (Web Text))

Max Activating Token Index: 454

Text #14

Max Range: 2.0122. Min Range: -2.0122

Max Act: 1.5310. Min Act: -0.0000

Data Index: 271289 (C4 (Web Text))

Max Activating Token Index: 388

Text #15

Max Range: 2.0122. Min Range: -2.0122

Max Act: 1.1965. Min Act: -0.0000

Data Index: 1237265 (C4 (Web Text))

Max Activating Token Index: 368

Text #16

Max Range: 2.0122. Min Range: -2.0122

Max Act: 1.2377. Min Act: -0.0000

Data Index: 926212 (C4 (Web Text))

Max Activating Token Index: 282

Text #17

Max Range: 2.0122. Min Range: -2.0122

Max Act: 1.2452. Min Act: -0.0000

Data Index: 1311846 (C4 (Web Text))

Max Activating Token Index: 506

Text #18

Max Range: 2.0122. Min Range: -2.0122

Max Act: 1.2449. Min Act: -0.0000

Data Index: 460257 (C4 (Web Text))

Max Activating Token Index: 185

Text #19

Max Range: 2.0122. Min Range: -2.0122

Max Act: 1.3060. Min Act: -0.0000

Data Index: 630085 (C4 (Web Text))

Max Activating Token Index: 320