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

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

Neuron 2320 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1513. Min Range: -1.1513

Max Act: 1.1513. Min Act: -0.0000

Data Index: 661984 (C4 (Web Text))

Max Activating Token Index: 319

Text #1

Max Range: 1.1513. Min Range: -1.1513

Max Act: 0.6997. Min Act: -0.0000

Data Index: 492725 (C4 (Web Text))

Max Activating Token Index: 576

Text #2

Max Range: 1.1513. Min Range: -1.1513

Max Act: 0.6988. Min Act: -0.0000

Data Index: 35140 (C4 (Web Text))

Max Activating Token Index: 479

Text #3

Max Range: 1.1513. Min Range: -1.1513

Max Act: 0.6888. Min Act: -0.0000

Data Index: 806635 (C4 (Web Text))

Max Activating Token Index: 309

Text #4

Max Range: 1.1513. Min Range: -1.1513

Max Act: 0.6424. Min Act: -0.0000

Data Index: 1024964 (C4 (Web Text))

Max Activating Token Index: 533

Text #5

Max Range: 1.1513. Min Range: -1.1513

Max Act: 0.6028. Min Act: 0.0001

Data Index: 730376 (C4 (Web Text))

Max Activating Token Index: 558

Text #6

Max Range: 1.1513. Min Range: -1.1513

Max Act: 0.6329. Min Act: -0.0000

Data Index: 707173 (C4 (Web Text))

Max Activating Token Index: 963

Text #7

Max Range: 1.1513. Min Range: -1.1513

Max Act: 0.6187. Min Act: -0.0000

Data Index: 337935 (C4 (Web Text))

Max Activating Token Index: 833

Text #8

Max Range: 1.1513. Min Range: -1.1513

Max Act: 0.6037. Min Act: -0.0000

Data Index: 1016402 (C4 (Web Text))

Max Activating Token Index: 272

Text #9

Max Range: 1.1513. Min Range: -1.1513

Max Act: 0.5648. Min Act: -0.0000

Data Index: 179915 (C4 (Web Text))

Max Activating Token Index: 653

Text #10

Max Range: 1.1513. Min Range: -1.1513

Max Act: 0.5813. Min Act: -0.0000

Data Index: 70990 (C4 (Web Text))

Max Activating Token Index: 611

Text #11

Max Range: 1.1513. Min Range: -1.1513

Max Act: 0.5874. Min Act: -0.0000

Data Index: 83593 (C4 (Web Text))

Max Activating Token Index: 252

Text #12

Max Range: 1.1513. Min Range: -1.1513

Max Act: 0.5843. Min Act: -0.0000

Data Index: 470929 (C4 (Web Text))

Max Activating Token Index: 334

Text #13

Max Range: 1.1513. Min Range: -1.1513

Max Act: 0.6108. Min Act: -0.0000

Data Index: 3217 (C4 (Web Text))

Max Activating Token Index: 496

Text #14

Max Range: 1.1513. Min Range: -1.1513

Max Act: 0.5705. Min Act: -0.0000

Data Index: 65522 (C4 (Web Text))

Max Activating Token Index: 610

Text #15

Max Range: 1.1513. Min Range: -1.1513

Max Act: 0.5664. Min Act: 0.0001

Data Index: 1237825 (C4 (Web Text))

Max Activating Token Index: 167

Text #16

Max Range: 1.1513. Min Range: -1.1513

Max Act: 0.5598. Min Act: -0.0000

Data Index: 502034 (C4 (Web Text))

Max Activating Token Index: 884

Text #17

Max Range: 1.1513. Min Range: -1.1513

Max Act: 0.5179. Min Act: -0.0000

Data Index: 821090 (C4 (Web Text))

Max Activating Token Index: 640

Text #18

Max Range: 1.1513. Min Range: -1.1513

Max Act: 0.5486. Min Act: -0.0000

Data Index: 275454 (C4 (Web Text))

Max Activating Token Index: 281

Text #19

Max Range: 1.1513. Min Range: -1.1513

Max Act: 0.5494. Min Act: -0.0000

Data Index: 76779 (C4 (Web Text))

Max Activating Token Index: 320