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

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

Neuron 3173 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: 2.0498. Min Range: -2.0498

Max Act: 2.0498. Min Act: -0.0000

Data Index: 242633 (C4 (Web Text))

Max Activating Token Index: 894

Text #1

Max Range: 2.0498. Min Range: -2.0498

Max Act: 1.6242. Min Act: -0.0000

Data Index: 801497 (C4 (Web Text))

Max Activating Token Index: 919

Text #2

Max Range: 2.0498. Min Range: -2.0498

Max Act: 1.6764. Min Act: -0.0000

Data Index: 938312 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 2.0498. Min Range: -2.0498

Max Act: 1.6636. Min Act: -0.0000

Data Index: 276349 (C4 (Web Text))

Max Activating Token Index: 793

Text #4

Max Range: 2.0498. Min Range: -2.0498

Max Act: 1.6419. Min Act: -0.0000

Data Index: 1061799 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 2.0498. Min Range: -2.0498

Max Act: 1.6423. Min Act: -0.0000

Data Index: 1291495 (C4 (Web Text))

Max Activating Token Index: 816

Text #6

Max Range: 2.0498. Min Range: -2.0498

Max Act: 1.6330. Min Act: -0.0000

Data Index: 690099 (C4 (Web Text))

Max Activating Token Index: 567

Text #7

Max Range: 2.0498. Min Range: -2.0498

Max Act: 1.5982. Min Act: -0.0000

Data Index: 986428 (C4 (Web Text))

Max Activating Token Index: 463

Text #8

Max Range: 2.0498. Min Range: -2.0498

Max Act: 1.5277. Min Act: -0.0000

Data Index: 315823 (C4 (Web Text))

Max Activating Token Index: 691

Text #9

Max Range: 2.0498. Min Range: -2.0498

Max Act: 1.5354. Min Act: -0.0000

Data Index: 1240791 (C4 (Web Text))

Max Activating Token Index: 694

Text #10

Max Range: 2.0498. Min Range: -2.0498

Max Act: 1.5518. Min Act: -0.0000

Data Index: 1268246 (C4 (Web Text))

Max Activating Token Index: 707

Text #11

Max Range: 2.0498. Min Range: -2.0498

Max Act: 1.4393. Min Act: -0.0000

Data Index: 918451 (C4 (Web Text))

Max Activating Token Index: 742

Text #12

Max Range: 2.0498. Min Range: -2.0498

Max Act: 1.3726. Min Act: -0.0000

Data Index: 1034436 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 2.0498. Min Range: -2.0498

Max Act: 1.5399. Min Act: -0.0000

Data Index: 1230379 (C4 (Web Text))

Max Activating Token Index: 170

Text #14

Max Range: 2.0498. Min Range: -2.0498

Max Act: 1.4347. Min Act: -0.0000

Data Index: 394316 (C4 (Web Text))

Max Activating Token Index: 79

Text #15

Max Range: 2.0498. Min Range: -2.0498

Max Act: 1.4923. Min Act: -0.0000

Data Index: 784231 (C4 (Web Text))

Max Activating Token Index: 981

Text #16

Max Range: 2.0498. Min Range: -2.0498

Max Act: 1.3783. Min Act: -0.0000

Data Index: 459567 (C4 (Web Text))

Max Activating Token Index: 304

Text #17

Max Range: 2.0498. Min Range: -2.0498

Max Act: 1.3917. Min Act: -0.0000

Data Index: 1172575 (C4 (Web Text))

Max Activating Token Index: 407

Text #18

Max Range: 2.0498. Min Range: -2.0498

Max Act: 1.3938. Min Act: -0.0000

Data Index: 629798 (C4 (Web Text))

Max Activating Token Index: 964

Text #19

Max Range: 2.0498. Min Range: -2.0498

Max Act: 1.2944. Min Act: -0.0000

Data Index: 445072 (C4 (Web Text))

Max Activating Token Index: 716