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

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

Neuron 2165 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.7300. Min Act: -0.0000

Data Index: 1350188 (C4 (Web Text))

Max Activating Token Index: 562

Text #1

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.7048. Min Act: -0.0000

Data Index: 838348 (C4 (Web Text))

Max Activating Token Index: 316

Text #2

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.6705. Min Act: -0.0000

Data Index: 449626 (C4 (Web Text))

Max Activating Token Index: 271

Text #3

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.6104. Min Act: -0.0000

Data Index: 1194331 (C4 (Web Text))

Max Activating Token Index: 239

Text #4

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.5707. Min Act: -0.0000

Data Index: 1303298 (C4 (Web Text))

Max Activating Token Index: 783

Text #5

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.5190. Min Act: -0.0000

Data Index: 1327798 (C4 (Web Text))

Max Activating Token Index: 353

Text #6

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.5228. Min Act: -0.0000

Data Index: 579257 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.5544. Min Act: -0.0000

Data Index: 512628 (C4 (Web Text))

Max Activating Token Index: 332

Text #8

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.5041. Min Act: -0.0000

Data Index: 1045636 (C4 (Web Text))

Max Activating Token Index: 244

Text #9

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.5329. Min Act: -0.0000

Data Index: 1068534 (C4 (Web Text))

Max Activating Token Index: 330

Text #10

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.4838. Min Act: -0.0000

Data Index: 568554 (C4 (Web Text))

Max Activating Token Index: 946

Text #11

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.4910. Min Act: -0.0000

Data Index: 1085767 (C4 (Web Text))

Max Activating Token Index: 535

Text #12

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.4769. Min Act: -0.0000

Data Index: 273742 (C4 (Web Text))

Max Activating Token Index: 185

Text #13

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.4785. Min Act: -0.0000

Data Index: 600704 (C4 (Web Text))

Max Activating Token Index: 654

Text #14

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.4748. Min Act: -0.0000

Data Index: 907489 (C4 (Web Text))

Max Activating Token Index: 513

Text #15

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.4552. Min Act: -0.0000

Data Index: 1588244 (Python Code)

Max Activating Token Index: 310

Text #16

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.4687. Min Act: 0.0000

Data Index: 1078391 (C4 (Web Text))

Max Activating Token Index: 800

Text #17

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.4004. Min Act: -0.0000

Data Index: 1648503 (Python Code)

Max Activating Token Index: 500

Text #18

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.3796. Min Act: -0.0000

Data Index: 739108 (C4 (Web Text))

Max Activating Token Index: 244

Text #19

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.3741. Min Act: -0.0000

Data Index: 1016762 (C4 (Web Text))

Max Activating Token Index: 17