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

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

Neuron 1704 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1893. Min Range: -1.1893

Max Act: 1.1893. Min Act: -0.0000

Data Index: 338363 (C4 (Web Text))

Max Activating Token Index: 396

Text #1

Max Range: 1.1893. Min Range: -1.1893

Max Act: 0.9021. Min Act: -0.0000

Data Index: 1200353 (C4 (Web Text))

Max Activating Token Index: 492

Text #2

Max Range: 1.1893. Min Range: -1.1893

Max Act: 0.9097. Min Act: -0.0000

Data Index: 615036 (C4 (Web Text))

Max Activating Token Index: 553

Text #3

Max Range: 1.1893. Min Range: -1.1893

Max Act: 0.7910. Min Act: -0.0000

Data Index: 1255643 (C4 (Web Text))

Max Activating Token Index: 846

Text #4

Max Range: 1.1893. Min Range: -1.1893

Max Act: 0.8078. Min Act: -0.0000

Data Index: 714600 (C4 (Web Text))

Max Activating Token Index: 686

Text #5

Max Range: 1.1893. Min Range: -1.1893

Max Act: 0.7330. Min Act: -0.0000

Data Index: 891431 (C4 (Web Text))

Max Activating Token Index: 625

Text #6

Max Range: 1.1893. Min Range: -1.1893

Max Act: 0.7669. Min Act: -0.0000

Data Index: 1063392 (C4 (Web Text))

Max Activating Token Index: 714

Text #7

Max Range: 1.1893. Min Range: -1.1893

Max Act: 0.8790. Min Act: -0.0000

Data Index: 869975 (C4 (Web Text))

Max Activating Token Index: 952

Text #8

Max Range: 1.1893. Min Range: -1.1893

Max Act: 0.6974. Min Act: -0.0000

Data Index: 573961 (C4 (Web Text))

Max Activating Token Index: 327

Text #9

Max Range: 1.1893. Min Range: -1.1893

Max Act: 0.7183. Min Act: -0.0000

Data Index: 699449 (C4 (Web Text))

Max Activating Token Index: 414

Text #10

Max Range: 1.1893. Min Range: -1.1893

Max Act: 0.7578. Min Act: -0.0000

Data Index: 236151 (C4 (Web Text))

Max Activating Token Index: 1017

Text #11

Max Range: 1.1893. Min Range: -1.1893

Max Act: 0.7514. Min Act: -0.0000

Data Index: 787162 (C4 (Web Text))

Max Activating Token Index: 564

Text #12

Max Range: 1.1893. Min Range: -1.1893

Max Act: 0.7370. Min Act: -0.0000

Data Index: 595130 (C4 (Web Text))

Max Activating Token Index: 677

Text #13

Max Range: 1.1893. Min Range: -1.1893

Max Act: 0.7225. Min Act: -0.0000

Data Index: 246425 (C4 (Web Text))

Max Activating Token Index: 262

Text #14

Max Range: 1.1893. Min Range: -1.1893

Max Act: 0.7180. Min Act: -0.0000

Data Index: 484151 (C4 (Web Text))

Max Activating Token Index: 309

Text #15

Max Range: 1.1893. Min Range: -1.1893

Max Act: 0.7283. Min Act: -0.0000

Data Index: 1032412 (C4 (Web Text))

Max Activating Token Index: 363

Text #16

Max Range: 1.1893. Min Range: -1.1893

Max Act: 0.7041. Min Act: -0.0000

Data Index: 95095 (C4 (Web Text))

Max Activating Token Index: 111

Text #17

Max Range: 1.1893. Min Range: -1.1893

Max Act: 0.6771. Min Act: -0.0000

Data Index: 990820 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 1.1893. Min Range: -1.1893

Max Act: 0.6774. Min Act: -0.0000

Data Index: 358662 (C4 (Web Text))

Max Activating Token Index: 670

Text #19

Max Range: 1.1893. Min Range: -1.1893

Max Act: 0.6540. Min Act: -0.0000

Data Index: 950742 (C4 (Web Text))

Max Activating Token Index: 684