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

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

Neuron 3013 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3454. Min Range: -1.3454

Max Act: 1.3454. Min Act: -0.0000

Data Index: 901875 (C4 (Web Text))

Max Activating Token Index: 496

Text #1

Max Range: 1.3454. Min Range: -1.3454

Max Act: 1.3416. Min Act: -0.0000

Data Index: 757926 (C4 (Web Text))

Max Activating Token Index: 168

Text #2

Max Range: 1.3454. Min Range: -1.3454

Max Act: 1.2617. Min Act: -0.0000

Data Index: 95325 (C4 (Web Text))

Max Activating Token Index: 94

Text #3

Max Range: 1.3454. Min Range: -1.3454

Max Act: 1.2584. Min Act: -0.0000

Data Index: 940762 (C4 (Web Text))

Max Activating Token Index: 539

Text #4

Max Range: 1.3454. Min Range: -1.3454

Max Act: 1.2350. Min Act: -0.0000

Data Index: 591651 (C4 (Web Text))

Max Activating Token Index: 557

Text #5

Max Range: 1.3454. Min Range: -1.3454

Max Act: 1.1451. Min Act: -0.0000

Data Index: 322776 (C4 (Web Text))

Max Activating Token Index: 972

Text #6

Max Range: 1.3454. Min Range: -1.3454

Max Act: 1.1968. Min Act: -0.0000

Data Index: 756280 (C4 (Web Text))

Max Activating Token Index: 251

Text #7

Max Range: 1.3454. Min Range: -1.3454

Max Act: 1.2023. Min Act: -0.0000

Data Index: 1344163 (C4 (Web Text))

Max Activating Token Index: 455

Text #8

Max Range: 1.3454. Min Range: -1.3454

Max Act: 1.2881. Min Act: -0.0000

Data Index: 312868 (C4 (Web Text))

Max Activating Token Index: 804

Text #9

Max Range: 1.3454. Min Range: -1.3454

Max Act: 1.1334. Min Act: -0.0000

Data Index: 129354 (C4 (Web Text))

Max Activating Token Index: 428

Text #10

Max Range: 1.3454. Min Range: -1.3454

Max Act: 1.0602. Min Act: -0.0000

Data Index: 106328 (C4 (Web Text))

Max Activating Token Index: 408

Text #11

Max Range: 1.3454. Min Range: -1.3454

Max Act: 1.1940. Min Act: -0.0000

Data Index: 1023925 (C4 (Web Text))

Max Activating Token Index: 352

Text #12

Max Range: 1.3454. Min Range: -1.3454

Max Act: 1.1125. Min Act: -0.0000

Data Index: 345735 (C4 (Web Text))

Max Activating Token Index: 396

Text #13

Max Range: 1.3454. Min Range: -1.3454

Max Act: 1.0092. Min Act: -0.0000

Data Index: 53464 (C4 (Web Text))

Max Activating Token Index: 847

Text #14

Max Range: 1.3454. Min Range: -1.3454

Max Act: 1.0607. Min Act: -0.0000

Data Index: 175816 (C4 (Web Text))

Max Activating Token Index: 1005

Text #15

Max Range: 1.3454. Min Range: -1.3454

Max Act: 0.9754. Min Act: -0.0000

Data Index: 210981 (C4 (Web Text))

Max Activating Token Index: 348

Text #16

Max Range: 1.3454. Min Range: -1.3454

Max Act: 1.0205. Min Act: -0.0000

Data Index: 1330029 (C4 (Web Text))

Max Activating Token Index: 604

Text #17

Max Range: 1.3454. Min Range: -1.3454

Max Act: 1.0371. Min Act: -0.0000

Data Index: 249822 (C4 (Web Text))

Max Activating Token Index: 403

Text #18

Max Range: 1.3454. Min Range: -1.3454

Max Act: 1.0345. Min Act: -0.0000

Data Index: 1128065 (C4 (Web Text))

Max Activating Token Index: 955

Text #19

Max Range: 1.3454. Min Range: -1.3454

Max Act: 0.9007. Min Act: -0.0000

Data Index: 1332674 (C4 (Web Text))

Max Activating Token Index: 354