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

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

Neuron 5803 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: 2.2763. Min Range: -2.2763

Max Act: 2.2763. Min Act: -0.0000

Data Index: 543148 (C4 (Web Text))

Max Activating Token Index: 409

Text #1

Max Range: 2.2763. Min Range: -2.2763

Max Act: 1.9040. Min Act: -0.0000

Data Index: 94761 (C4 (Web Text))

Max Activating Token Index: 1020

Text #2

Max Range: 2.2763. Min Range: -2.2763

Max Act: 1.8643. Min Act: -0.0000

Data Index: 185907 (C4 (Web Text))

Max Activating Token Index: 525

Text #3

Max Range: 2.2763. Min Range: -2.2763

Max Act: 1.8982. Min Act: -0.0000

Data Index: 183250 (C4 (Web Text))

Max Activating Token Index: 455

Text #4

Max Range: 2.2763. Min Range: -2.2763

Max Act: 1.8650. Min Act: -0.0000

Data Index: 392249 (C4 (Web Text))

Max Activating Token Index: 380

Text #5

Max Range: 2.2763. Min Range: -2.2763

Max Act: 1.8211. Min Act: -0.0000

Data Index: 1415676 (Python Code)

Max Activating Token Index: 471

Text #6

Max Range: 2.2763. Min Range: -2.2763

Max Act: 1.7588. Min Act: -0.0000

Data Index: 458881 (C4 (Web Text))

Max Activating Token Index: 554

Text #7

Max Range: 2.2763. Min Range: -2.2763

Max Act: 1.5993. Min Act: -0.0000

Data Index: 481084 (C4 (Web Text))

Max Activating Token Index: 542

Text #8

Max Range: 2.2763. Min Range: -2.2763

Max Act: 1.5680. Min Act: -0.0000

Data Index: 281399 (C4 (Web Text))

Max Activating Token Index: 146

Text #9

Max Range: 2.2763. Min Range: -2.2763

Max Act: 1.5876. Min Act: -0.0000

Data Index: 319030 (C4 (Web Text))

Max Activating Token Index: 641

Text #10

Max Range: 2.2763. Min Range: -2.2763

Max Act: 1.5687. Min Act: -0.0000

Data Index: 813636 (C4 (Web Text))

Max Activating Token Index: 385

Text #11

Max Range: 2.2763. Min Range: -2.2763

Max Act: 1.6708. Min Act: -0.0000

Data Index: 911586 (C4 (Web Text))

Max Activating Token Index: 715

Text #12

Max Range: 2.2763. Min Range: -2.2763

Max Act: 1.7759. Min Act: -0.0000

Data Index: 1277138 (C4 (Web Text))

Max Activating Token Index: 822

Text #13

Max Range: 2.2763. Min Range: -2.2763

Max Act: 1.7195. Min Act: -0.0000

Data Index: 1373452 (Python Code)

Max Activating Token Index: 879

Text #14

Max Range: 2.2763. Min Range: -2.2763

Max Act: 1.4309. Min Act: -0.0000

Data Index: 733580 (C4 (Web Text))

Max Activating Token Index: 794

Text #15

Max Range: 2.2763. Min Range: -2.2763

Max Act: 1.4494. Min Act: -0.0000

Data Index: 1132370 (C4 (Web Text))

Max Activating Token Index: 361

Text #16

Max Range: 2.2763. Min Range: -2.2763

Max Act: 1.5243. Min Act: -0.0000

Data Index: 463440 (C4 (Web Text))

Max Activating Token Index: 675

Text #17

Max Range: 2.2763. Min Range: -2.2763

Max Act: 1.5370. Min Act: -0.0000

Data Index: 142948 (C4 (Web Text))

Max Activating Token Index: 460

Text #18

Max Range: 2.2763. Min Range: -2.2763

Max Act: 1.6255. Min Act: -0.0000

Data Index: 1197113 (C4 (Web Text))

Max Activating Token Index: 446

Text #19

Max Range: 2.2763. Min Range: -2.2763

Max Act: 1.4639. Min Act: -0.0000

Data Index: 865652 (C4 (Web Text))

Max Activating Token Index: 751