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

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

Neuron 3896 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4314. Min Range: -2.4314

Max Act: 2.4314. Min Act: -0.0000

Data Index: 1285911 (C4 (Web Text))

Max Activating Token Index: 539

Text #1

Max Range: 2.4314. Min Range: -2.4314

Max Act: 1.3045. Min Act: -0.0000

Data Index: 274368 (C4 (Web Text))

Max Activating Token Index: 754

Text #2

Max Range: 2.4314. Min Range: -2.4314

Max Act: 1.4567. Min Act: -0.0000

Data Index: 729754 (C4 (Web Text))

Max Activating Token Index: 723

Text #3

Max Range: 2.4314. Min Range: -2.4314

Max Act: 1.3441. Min Act: -0.0000

Data Index: 714899 (C4 (Web Text))

Max Activating Token Index: 579

Text #4

Max Range: 2.4314. Min Range: -2.4314

Max Act: 1.2551. Min Act: -0.0000

Data Index: 516666 (C4 (Web Text))

Max Activating Token Index: 595

Text #5

Max Range: 2.4314. Min Range: -2.4314

Max Act: 1.4667. Min Act: -0.0000

Data Index: 1103751 (C4 (Web Text))

Max Activating Token Index: 1013

Text #6

Max Range: 2.4314. Min Range: -2.4314

Max Act: 1.3033. Min Act: -0.0000

Data Index: 371440 (C4 (Web Text))

Max Activating Token Index: 203

Text #7

Max Range: 2.4314. Min Range: -2.4314

Max Act: 1.2079. Min Act: 0.0000

Data Index: 388054 (C4 (Web Text))

Max Activating Token Index: 746

Text #8

Max Range: 2.4314. Min Range: -2.4314

Max Act: 1.1719. Min Act: -0.0000

Data Index: 1352896 (C4 (Web Text))

Max Activating Token Index: 701

Text #9

Max Range: 2.4314. Min Range: -2.4314

Max Act: 1.2274. Min Act: -0.0000

Data Index: 1159827 (C4 (Web Text))

Max Activating Token Index: 660

Text #10

Max Range: 2.4314. Min Range: -2.4314

Max Act: 1.1491. Min Act: -0.0000

Data Index: 1222464 (C4 (Web Text))

Max Activating Token Index: 518

Text #11

Max Range: 2.4314. Min Range: -2.4314

Max Act: 1.1385. Min Act: -0.0000

Data Index: 1314370 (C4 (Web Text))

Max Activating Token Index: 753

Text #12

Max Range: 2.4314. Min Range: -2.4314

Max Act: 1.1312. Min Act: -0.0000

Data Index: 231778 (C4 (Web Text))

Max Activating Token Index: 627

Text #13

Max Range: 2.4314. Min Range: -2.4314

Max Act: 1.1280. Min Act: -0.0000

Data Index: 718990 (C4 (Web Text))

Max Activating Token Index: 1016

Text #14

Max Range: 2.4314. Min Range: -2.4314

Max Act: 1.0417. Min Act: -0.0000

Data Index: 833363 (C4 (Web Text))

Max Activating Token Index: 311

Text #15

Max Range: 2.4314. Min Range: -2.4314

Max Act: 1.0820. Min Act: 0.0000

Data Index: 649258 (C4 (Web Text))

Max Activating Token Index: 463

Text #16

Max Range: 2.4314. Min Range: -2.4314

Max Act: 1.0056. Min Act: -0.0000

Data Index: 993135 (C4 (Web Text))

Max Activating Token Index: 460

Text #17

Max Range: 2.4314. Min Range: -2.4314

Max Act: 0.9991. Min Act: -0.0000

Data Index: 531458 (C4 (Web Text))

Max Activating Token Index: 688

Text #18

Max Range: 2.4314. Min Range: -2.4314

Max Act: 1.0521. Min Act: -0.0000

Data Index: 411305 (C4 (Web Text))

Max Activating Token Index: 556

Text #19

Max Range: 2.4314. Min Range: -2.4314

Max Act: 1.1146. Min Act: -0.0000

Data Index: 782332 (C4 (Web Text))

Max Activating Token Index: 417