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

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

Neuron 2585 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.2396. Min Range: -2.2396

Max Act: 2.2396. Min Act: -0.0000

Data Index: 987228 (C4 (Web Text))

Max Activating Token Index: 854

Text #1

Max Range: 2.2396. Min Range: -2.2396

Max Act: 2.0731. Min Act: -0.0000

Data Index: 949236 (C4 (Web Text))

Max Activating Token Index: 461

Text #2

Max Range: 2.2396. Min Range: -2.2396

Max Act: 1.9908. Min Act: -0.0000

Data Index: 676495 (C4 (Web Text))

Max Activating Token Index: 300

Text #3

Max Range: 2.2396. Min Range: -2.2396

Max Act: 2.0218. Min Act: -0.0000

Data Index: 354997 (C4 (Web Text))

Max Activating Token Index: 527

Text #4

Max Range: 2.2396. Min Range: -2.2396

Max Act: 2.0236. Min Act: -0.0000

Data Index: 1046013 (C4 (Web Text))

Max Activating Token Index: 451

Text #5

Max Range: 2.2396. Min Range: -2.2396

Max Act: 1.9106. Min Act: -0.0000

Data Index: 455561 (C4 (Web Text))

Max Activating Token Index: 910

Text #6

Max Range: 2.2396. Min Range: -2.2396

Max Act: 1.9886. Min Act: -0.0000

Data Index: 1300753 (C4 (Web Text))

Max Activating Token Index: 810

Text #7

Max Range: 2.2396. Min Range: -2.2396

Max Act: 1.8612. Min Act: -0.0000

Data Index: 73872 (C4 (Web Text))

Max Activating Token Index: 8

Text #8

Max Range: 2.2396. Min Range: -2.2396

Max Act: 1.9633. Min Act: -0.0000

Data Index: 2869 (C4 (Web Text))

Max Activating Token Index: 477

Text #9

Max Range: 2.2396. Min Range: -2.2396

Max Act: 1.9703. Min Act: -0.0000

Data Index: 450684 (C4 (Web Text))

Max Activating Token Index: 702

Text #10

Max Range: 2.2396. Min Range: -2.2396

Max Act: 1.9268. Min Act: -0.0000

Data Index: 487422 (C4 (Web Text))

Max Activating Token Index: 45

Text #11

Max Range: 2.2396. Min Range: -2.2396

Max Act: 1.8599. Min Act: -0.0000

Data Index: 936484 (C4 (Web Text))

Max Activating Token Index: 726

Text #12

Max Range: 2.2396. Min Range: -2.2396

Max Act: 1.9337. Min Act: -0.0000

Data Index: 31763 (C4 (Web Text))

Max Activating Token Index: 288

Text #13

Max Range: 2.2396. Min Range: -2.2396

Max Act: 1.8110. Min Act: -0.0000

Data Index: 270655 (C4 (Web Text))

Max Activating Token Index: 295

Text #14

Max Range: 2.2396. Min Range: -2.2396

Max Act: 1.6712. Min Act: -0.0000

Data Index: 342801 (C4 (Web Text))

Max Activating Token Index: 253

Text #15

Max Range: 2.2396. Min Range: -2.2396

Max Act: 1.7470. Min Act: -0.0000

Data Index: 1233749 (C4 (Web Text))

Max Activating Token Index: 505

Text #16

Max Range: 2.2396. Min Range: -2.2396

Max Act: 1.6558. Min Act: -0.0000

Data Index: 404169 (C4 (Web Text))

Max Activating Token Index: 20

Text #17

Max Range: 2.2396. Min Range: -2.2396

Max Act: 1.8150. Min Act: -0.0000

Data Index: 627244 (C4 (Web Text))

Max Activating Token Index: 445

Text #18

Max Range: 2.2396. Min Range: -2.2396

Max Act: 1.8009. Min Act: -0.0000

Data Index: 852616 (C4 (Web Text))

Max Activating Token Index: 8

Text #19

Max Range: 2.2396. Min Range: -2.2396

Max Act: 1.5158. Min Act: -0.0000

Data Index: 997644 (C4 (Web Text))

Max Activating Token Index: 235