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

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

Neuron 1880 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: 0.4346. Min Range: -0.4346

Max Act: 0.4346. Min Act: -0.0000

Data Index: 1382128 (Python Code)

Max Activating Token Index: 50

Text #1

Max Range: 0.4346. Min Range: -0.4346

Max Act: 0.4148. Min Act: -0.0000

Data Index: 578913 (C4 (Web Text))

Max Activating Token Index: 903

Text #2

Max Range: 0.4346. Min Range: -0.4346

Max Act: 0.4203. Min Act: -0.0000

Data Index: 360401 (C4 (Web Text))

Max Activating Token Index: 362

Text #3

Max Range: 0.4346. Min Range: -0.4346

Max Act: 0.4142. Min Act: -0.0000

Data Index: 1565027 (Python Code)

Max Activating Token Index: 70

Text #4

Max Range: 0.4346. Min Range: -0.4346

Max Act: 0.3831. Min Act: -0.0000

Data Index: 1328690 (C4 (Web Text))

Max Activating Token Index: 161

Text #5

Max Range: 0.4346. Min Range: -0.4346

Max Act: 0.3818. Min Act: -0.0000

Data Index: 1312378 (C4 (Web Text))

Max Activating Token Index: 590

Text #6

Max Range: 0.4346. Min Range: -0.4346

Max Act: 0.3670. Min Act: -0.0000

Data Index: 1248303 (C4 (Web Text))

Max Activating Token Index: 344

Text #7

Max Range: 0.4346. Min Range: -0.4346

Max Act: 0.3747. Min Act: -0.0000

Data Index: 299575 (C4 (Web Text))

Max Activating Token Index: 243

Text #8

Max Range: 0.4346. Min Range: -0.4346

Max Act: 0.3545. Min Act: -0.0000

Data Index: 878381 (C4 (Web Text))

Max Activating Token Index: 54

Text #9

Max Range: 0.4346. Min Range: -0.4346

Max Act: 0.3963. Min Act: -0.0000

Data Index: 28576 (C4 (Web Text))

Max Activating Token Index: 643

Text #10

Max Range: 0.4346. Min Range: -0.4346

Max Act: 0.3370. Min Act: -0.0000

Data Index: 485325 (C4 (Web Text))

Max Activating Token Index: 806

Text #11

Max Range: 0.4346. Min Range: -0.4346

Max Act: 0.3616. Min Act: -0.0000

Data Index: 636947 (C4 (Web Text))

Max Activating Token Index: 273

Text #12

Max Range: 0.4346. Min Range: -0.4346

Max Act: 0.3354. Min Act: -0.0000

Data Index: 337686 (C4 (Web Text))

Max Activating Token Index: 316

Text #13

Max Range: 0.4346. Min Range: -0.4346

Max Act: 0.3417. Min Act: -0.0000

Data Index: 1507053 (Python Code)

Max Activating Token Index: 78

Text #14

Max Range: 0.4346. Min Range: -0.4346

Max Act: 0.3654. Min Act: -0.0000

Data Index: 919773 (C4 (Web Text))

Max Activating Token Index: 230

Text #15

Max Range: 0.4346. Min Range: -0.4346

Max Act: 0.3761. Min Act: -0.0000

Data Index: 674690 (C4 (Web Text))

Max Activating Token Index: 635

Text #16

Max Range: 0.4346. Min Range: -0.4346

Max Act: 0.3387. Min Act: -0.0000

Data Index: 669897 (C4 (Web Text))

Max Activating Token Index: 654

Text #17

Max Range: 0.4346. Min Range: -0.4346

Max Act: 0.3352. Min Act: -0.0000

Data Index: 496902 (C4 (Web Text))

Max Activating Token Index: 37

Text #18

Max Range: 0.4346. Min Range: -0.4346

Max Act: 0.3307. Min Act: -0.0000

Data Index: 1180165 (C4 (Web Text))

Max Activating Token Index: 764

Text #19

Max Range: 0.4346. Min Range: -0.4346

Max Act: 0.3508. Min Act: -0.0000

Data Index: 127346 (C4 (Web Text))

Max Activating Token Index: 444