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

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

Neuron 1548 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6558. Min Range: -1.6558

Max Act: 1.6558. Min Act: -0.0000

Data Index: 1411541 (Python Code)

Max Activating Token Index: 822

Text #1

Max Range: 1.6558. Min Range: -1.6558

Max Act: 1.6253. Min Act: -0.0000

Data Index: 425853 (C4 (Web Text))

Max Activating Token Index: 453

Text #2

Max Range: 1.6558. Min Range: -1.6558

Max Act: 1.4374. Min Act: -0.0000

Data Index: 1595236 (Python Code)

Max Activating Token Index: 303

Text #3

Max Range: 1.6558. Min Range: -1.6558

Max Act: 1.3842. Min Act: -0.0000

Data Index: 1597181 (Python Code)

Max Activating Token Index: 887

Text #4

Max Range: 1.6558. Min Range: -1.6558

Max Act: 1.4901. Min Act: -0.0000

Data Index: 1541132 (Python Code)

Max Activating Token Index: 712

Text #5

Max Range: 1.6558. Min Range: -1.6558

Max Act: 1.3756. Min Act: -0.0000

Data Index: 1389703 (Python Code)

Max Activating Token Index: 434

Text #6

Max Range: 1.6558. Min Range: -1.6558

Max Act: 1.4123. Min Act: -0.0000

Data Index: 1461614 (Python Code)

Max Activating Token Index: 289

Text #7

Max Range: 1.6558. Min Range: -1.6558

Max Act: 1.3512. Min Act: -0.0000

Data Index: 1502710 (Python Code)

Max Activating Token Index: 317

Text #8

Max Range: 1.6558. Min Range: -1.6558

Max Act: 1.3179. Min Act: -0.0000

Data Index: 1586548 (Python Code)

Max Activating Token Index: 320

Text #9

Max Range: 1.6558. Min Range: -1.6558

Max Act: 1.3224. Min Act: -0.0000

Data Index: 1380509 (Python Code)

Max Activating Token Index: 887

Text #10

Max Range: 1.6558. Min Range: -1.6558

Max Act: 1.2921. Min Act: -0.0000

Data Index: 1449897 (Python Code)

Max Activating Token Index: 158

Text #11

Max Range: 1.6558. Min Range: -1.6558

Max Act: 1.1768. Min Act: -0.0000

Data Index: 1484327 (Python Code)

Max Activating Token Index: 778

Text #12

Max Range: 1.6558. Min Range: -1.6558

Max Act: 1.3069. Min Act: -0.0000

Data Index: 1364383 (Python Code)

Max Activating Token Index: 477

Text #13

Max Range: 1.6558. Min Range: -1.6558

Max Act: 1.2571. Min Act: -0.0000

Data Index: 1524110 (Python Code)

Max Activating Token Index: 629

Text #14

Max Range: 1.6558. Min Range: -1.6558

Max Act: 1.3193. Min Act: -0.0000

Data Index: 1437899 (Python Code)

Max Activating Token Index: 425

Text #15

Max Range: 1.6558. Min Range: -1.6558

Max Act: 1.3928. Min Act: -0.0000

Data Index: 1396572 (Python Code)

Max Activating Token Index: 522

Text #16

Max Range: 1.6558. Min Range: -1.6558

Max Act: 1.2704. Min Act: -0.0000

Data Index: 1364761 (Python Code)

Max Activating Token Index: 407

Text #17

Max Range: 1.6558. Min Range: -1.6558

Max Act: 1.2261. Min Act: -0.0000

Data Index: 1635357 (Python Code)

Max Activating Token Index: 877

Text #18

Max Range: 1.6558. Min Range: -1.6558

Max Act: 1.2858. Min Act: -0.0000

Data Index: 1504231 (Python Code)

Max Activating Token Index: 705

Text #19

Max Range: 1.6558. Min Range: -1.6558

Max Act: 1.2145. Min Act: -0.0000

Data Index: 1412954 (Python Code)

Max Activating Token Index: 928