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

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

Neuron 2173 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2100. Min Range: -1.2100

Max Act: 1.2100. Min Act: -0.0001

Data Index: 399512 (C4 (Web Text))

Max Activating Token Index: 315

Text #1

Max Range: 1.2100. Min Range: -1.2100

Max Act: 1.1288. Min Act: -0.0001

Data Index: 165858 (C4 (Web Text))

Max Activating Token Index: 533

Text #2

Max Range: 1.2100. Min Range: -1.2100

Max Act: 0.9572. Min Act: -0.0002

Data Index: 238721 (C4 (Web Text))

Max Activating Token Index: 344

Text #3

Max Range: 1.2100. Min Range: -1.2100

Max Act: 0.9405. Min Act: -0.0001

Data Index: 997148 (C4 (Web Text))

Max Activating Token Index: 705

Text #4

Max Range: 1.2100. Min Range: -1.2100

Max Act: 1.0018. Min Act: -0.0001

Data Index: 628661 (C4 (Web Text))

Max Activating Token Index: 173

Text #5

Max Range: 1.2100. Min Range: -1.2100

Max Act: 0.9694. Min Act: -0.0001

Data Index: 891317 (C4 (Web Text))

Max Activating Token Index: 961

Text #6

Max Range: 1.2100. Min Range: -1.2100

Max Act: 0.9204. Min Act: -0.0001

Data Index: 1643303 (Python Code)

Max Activating Token Index: 320

Text #7

Max Range: 1.2100. Min Range: -1.2100

Max Act: 0.9329. Min Act: -0.0001

Data Index: 1309755 (C4 (Web Text))

Max Activating Token Index: 660

Text #8

Max Range: 1.2100. Min Range: -1.2100

Max Act: 0.9662. Min Act: -0.0001

Data Index: 677885 (C4 (Web Text))

Max Activating Token Index: 504

Text #9

Max Range: 1.2100. Min Range: -1.2100

Max Act: 0.9351. Min Act: -0.0001

Data Index: 633354 (C4 (Web Text))

Max Activating Token Index: 93

Text #10

Max Range: 1.2100. Min Range: -1.2100

Max Act: 0.9632. Min Act: -0.0001

Data Index: 746211 (C4 (Web Text))

Max Activating Token Index: 498

Text #11

Max Range: 1.2100. Min Range: -1.2100

Max Act: 0.9270. Min Act: -0.0001

Data Index: 301484 (C4 (Web Text))

Max Activating Token Index: 358

Text #12

Max Range: 1.2100. Min Range: -1.2100

Max Act: 0.9258. Min Act: -0.0001

Data Index: 1062158 (C4 (Web Text))

Max Activating Token Index: 958

Text #13

Max Range: 1.2100. Min Range: -1.2100

Max Act: 0.9499. Min Act: -0.0001

Data Index: 1320686 (C4 (Web Text))

Max Activating Token Index: 855

Text #14

Max Range: 1.2100. Min Range: -1.2100

Max Act: 0.9792. Min Act: -0.0001

Data Index: 1022643 (C4 (Web Text))

Max Activating Token Index: 496

Text #15

Max Range: 1.2100. Min Range: -1.2100

Max Act: 0.9748. Min Act: -0.0001

Data Index: 1253667 (C4 (Web Text))

Max Activating Token Index: 599

Text #16

Max Range: 1.2100. Min Range: -1.2100

Max Act: 0.9278. Min Act: -0.0001

Data Index: 688699 (C4 (Web Text))

Max Activating Token Index: 455

Text #17

Max Range: 1.2100. Min Range: -1.2100

Max Act: 0.9016. Min Act: -0.0001

Data Index: 203147 (C4 (Web Text))

Max Activating Token Index: 746

Text #18

Max Range: 1.2100. Min Range: -1.2100

Max Act: 0.9124. Min Act: -0.0001

Data Index: 673395 (C4 (Web Text))

Max Activating Token Index: 869

Text #19

Max Range: 1.2100. Min Range: -1.2100

Max Act: 0.8598. Min Act: -0.0001

Data Index: 669616 (C4 (Web Text))

Max Activating Token Index: 772