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

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

Neuron 2267 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5905. Min Range: -0.5905

Max Act: 0.5905. Min Act: -0.0000

Data Index: 955942 (C4 (Web Text))

Max Activating Token Index: 530

Text #1

Max Range: 0.5905. Min Range: -0.5905

Max Act: 0.5213. Min Act: -0.0000

Data Index: 900267 (C4 (Web Text))

Max Activating Token Index: 267

Text #2

Max Range: 0.5905. Min Range: -0.5905

Max Act: 0.5060. Min Act: -0.0000

Data Index: 1392404 (Python Code)

Max Activating Token Index: 474

Text #3

Max Range: 0.5905. Min Range: -0.5905

Max Act: 0.5478. Min Act: -0.0000

Data Index: 1328048 (C4 (Web Text))

Max Activating Token Index: 395

Text #4

Max Range: 0.5905. Min Range: -0.5905

Max Act: 0.4777. Min Act: -0.0000

Data Index: 1513124 (Python Code)

Max Activating Token Index: 305

Text #5

Max Range: 0.5905. Min Range: -0.5905

Max Act: 0.4954. Min Act: -0.0000

Data Index: 558223 (C4 (Web Text))

Max Activating Token Index: 712

Text #6

Max Range: 0.5905. Min Range: -0.5905

Max Act: 0.5189. Min Act: -0.0000

Data Index: 725206 (C4 (Web Text))

Max Activating Token Index: 233

Text #7

Max Range: 0.5905. Min Range: -0.5905

Max Act: 0.4627. Min Act: -0.0000

Data Index: 1364158 (Python Code)

Max Activating Token Index: 304

Text #8

Max Range: 0.5905. Min Range: -0.5905

Max Act: 0.4663. Min Act: -0.0000

Data Index: 477150 (C4 (Web Text))

Max Activating Token Index: 990

Text #9

Max Range: 0.5905. Min Range: -0.5905

Max Act: 0.4487. Min Act: -0.0000

Data Index: 1581672 (Python Code)

Max Activating Token Index: 117

Text #10

Max Range: 0.5905. Min Range: -0.5905

Max Act: 0.4863. Min Act: -0.0000

Data Index: 1603449 (Python Code)

Max Activating Token Index: 171

Text #11

Max Range: 0.5905. Min Range: -0.5905

Max Act: 0.4247. Min Act: -0.0000

Data Index: 194847 (C4 (Web Text))

Max Activating Token Index: 140

Text #12

Max Range: 0.5905. Min Range: -0.5905

Max Act: 0.4565. Min Act: -0.0000

Data Index: 767356 (C4 (Web Text))

Max Activating Token Index: 528

Text #13

Max Range: 0.5905. Min Range: -0.5905

Max Act: 0.4434. Min Act: -0.0000

Data Index: 1632822 (Python Code)

Max Activating Token Index: 422

Text #14

Max Range: 0.5905. Min Range: -0.5905

Max Act: 0.4434. Min Act: -0.0000

Data Index: 1478282 (Python Code)

Max Activating Token Index: 73

Text #15

Max Range: 0.5905. Min Range: -0.5905

Max Act: 0.4428. Min Act: -0.0000

Data Index: 1360059 (Python Code)

Max Activating Token Index: 481

Text #16

Max Range: 0.5905. Min Range: -0.5905

Max Act: 0.4682. Min Act: -0.0000

Data Index: 168463 (C4 (Web Text))

Max Activating Token Index: 542

Text #17

Max Range: 0.5905. Min Range: -0.5905

Max Act: 0.4235. Min Act: -0.0000

Data Index: 1553442 (Python Code)

Max Activating Token Index: 78

Text #18

Max Range: 0.5905. Min Range: -0.5905

Max Act: 0.4486. Min Act: -0.0000

Data Index: 1356035 (C4 (Web Text))

Max Activating Token Index: 616

Text #19

Max Range: 0.5905. Min Range: -0.5905

Max Act: 0.4599. Min Act: -0.0000

Data Index: 1442742 (Python Code)

Max Activating Token Index: 308