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

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

Neuron 2783 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9169. Min Range: -2.9169

Max Act: 2.9169. Min Act: -0.0000

Data Index: 1268594 (C4 (Web Text))

Max Activating Token Index: 30

Text #1

Max Range: 2.9169. Min Range: -2.9169

Max Act: 2.6587. Min Act: -0.0000

Data Index: 810106 (C4 (Web Text))

Max Activating Token Index: 337

Text #2

Max Range: 2.9169. Min Range: -2.9169

Max Act: 2.3979. Min Act: -0.0000

Data Index: 33632 (C4 (Web Text))

Max Activating Token Index: 538

Text #3

Max Range: 2.9169. Min Range: -2.9169

Max Act: 2.5302. Min Act: -0.0000

Data Index: 850578 (C4 (Web Text))

Max Activating Token Index: 706

Text #4

Max Range: 2.9169. Min Range: -2.9169

Max Act: 2.3306. Min Act: -0.0000

Data Index: 1205510 (C4 (Web Text))

Max Activating Token Index: 830

Text #5

Max Range: 2.9169. Min Range: -2.9169

Max Act: 2.3245. Min Act: -0.0000

Data Index: 1309275 (C4 (Web Text))

Max Activating Token Index: 373

Text #6

Max Range: 2.9169. Min Range: -2.9169

Max Act: 2.2954. Min Act: -0.0000

Data Index: 435538 (C4 (Web Text))

Max Activating Token Index: 983

Text #7

Max Range: 2.9169. Min Range: -2.9169

Max Act: 2.3905. Min Act: -0.0000

Data Index: 737288 (C4 (Web Text))

Max Activating Token Index: 106

Text #8

Max Range: 2.9169. Min Range: -2.9169

Max Act: 2.2535. Min Act: -0.0000

Data Index: 1228292 (C4 (Web Text))

Max Activating Token Index: 48

Text #9

Max Range: 2.9169. Min Range: -2.9169

Max Act: 2.3307. Min Act: -0.0000

Data Index: 1034271 (C4 (Web Text))

Max Activating Token Index: 983

Text #10

Max Range: 2.9169. Min Range: -2.9169

Max Act: 2.2681. Min Act: -0.0000

Data Index: 762653 (C4 (Web Text))

Max Activating Token Index: 718

Text #11

Max Range: 2.9169. Min Range: -2.9169

Max Act: 2.3111. Min Act: -0.0000

Data Index: 294525 (C4 (Web Text))

Max Activating Token Index: 984

Text #12

Max Range: 2.9169. Min Range: -2.9169

Max Act: 2.2831. Min Act: -0.0000

Data Index: 341710 (C4 (Web Text))

Max Activating Token Index: 96

Text #13

Max Range: 2.9169. Min Range: -2.9169

Max Act: 2.1389. Min Act: -0.0000

Data Index: 534462 (C4 (Web Text))

Max Activating Token Index: 518

Text #14

Max Range: 2.9169. Min Range: -2.9169

Max Act: 2.1118. Min Act: -0.0000

Data Index: 1000270 (C4 (Web Text))

Max Activating Token Index: 21

Text #15

Max Range: 2.9169. Min Range: -2.9169

Max Act: 2.0959. Min Act: -0.0000

Data Index: 1213995 (C4 (Web Text))

Max Activating Token Index: 521

Text #16

Max Range: 2.9169. Min Range: -2.9169

Max Act: 1.9759. Min Act: -0.0000

Data Index: 456392 (C4 (Web Text))

Max Activating Token Index: 961

Text #17

Max Range: 2.9169. Min Range: -2.9169

Max Act: 1.9452. Min Act: -0.0000

Data Index: 555607 (C4 (Web Text))

Max Activating Token Index: 761

Text #18

Max Range: 2.9169. Min Range: -2.9169

Max Act: 1.9504. Min Act: -0.0000

Data Index: 384160 (C4 (Web Text))

Max Activating Token Index: 324

Text #19

Max Range: 2.9169. Min Range: -2.9169

Max Act: 1.8159. Min Act: -0.0000

Data Index: 753952 (C4 (Web Text))

Max Activating Token Index: 660