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

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

Neuron 646 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: 3.1274. Min Range: -3.1274

Max Act: 3.1274. Min Act: -0.0000

Data Index: 482302 (C4 (Web Text))

Max Activating Token Index: 207

Text #1

Max Range: 3.1274. Min Range: -3.1274

Max Act: 2.9967. Min Act: -0.0000

Data Index: 663024 (C4 (Web Text))

Max Activating Token Index: 331

Text #2

Max Range: 3.1274. Min Range: -3.1274

Max Act: 2.5709. Min Act: -0.0000

Data Index: 692598 (C4 (Web Text))

Max Activating Token Index: 630

Text #3

Max Range: 3.1274. Min Range: -3.1274

Max Act: 2.1940. Min Act: -0.0000

Data Index: 331467 (C4 (Web Text))

Max Activating Token Index: 381

Text #4

Max Range: 3.1274. Min Range: -3.1274

Max Act: 2.3016. Min Act: -0.0000

Data Index: 488433 (C4 (Web Text))

Max Activating Token Index: 463

Text #5

Max Range: 3.1274. Min Range: -3.1274

Max Act: 2.4055. Min Act: -0.0000

Data Index: 613586 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 3.1274. Min Range: -3.1274

Max Act: 2.6422. Min Act: -0.0000

Data Index: 88725 (C4 (Web Text))

Max Activating Token Index: 606

Text #7

Max Range: 3.1274. Min Range: -3.1274

Max Act: 2.2671. Min Act: -0.0000

Data Index: 817146 (C4 (Web Text))

Max Activating Token Index: 61

Text #8

Max Range: 3.1274. Min Range: -3.1274

Max Act: 2.5221. Min Act: -0.0000

Data Index: 269950 (C4 (Web Text))

Max Activating Token Index: 776

Text #9

Max Range: 3.1274. Min Range: -3.1274

Max Act: 2.2761. Min Act: -0.0000

Data Index: 761905 (C4 (Web Text))

Max Activating Token Index: 49

Text #10

Max Range: 3.1274. Min Range: -3.1274

Max Act: 2.3899. Min Act: -0.0000

Data Index: 991487 (C4 (Web Text))

Max Activating Token Index: 183

Text #11

Max Range: 3.1274. Min Range: -3.1274

Max Act: 2.1645. Min Act: -0.0000

Data Index: 686639 (C4 (Web Text))

Max Activating Token Index: 61

Text #12

Max Range: 3.1274. Min Range: -3.1274

Max Act: 2.1529. Min Act: -0.0000

Data Index: 1005533 (C4 (Web Text))

Max Activating Token Index: 496

Text #13

Max Range: 3.1274. Min Range: -3.1274

Max Act: 2.1298. Min Act: -0.0000

Data Index: 207745 (C4 (Web Text))

Max Activating Token Index: 155

Text #14

Max Range: 3.1274. Min Range: -3.1274

Max Act: 2.4977. Min Act: -0.0000

Data Index: 556694 (C4 (Web Text))

Max Activating Token Index: 712

Text #15

Max Range: 3.1274. Min Range: -3.1274

Max Act: 2.0688. Min Act: -0.0000

Data Index: 1218106 (C4 (Web Text))

Max Activating Token Index: 485

Text #16

Max Range: 3.1274. Min Range: -3.1274

Max Act: 2.0548. Min Act: -0.0000

Data Index: 222886 (C4 (Web Text))

Max Activating Token Index: 477

Text #17

Max Range: 3.1274. Min Range: -3.1274

Max Act: 2.1373. Min Act: -0.0000

Data Index: 966060 (C4 (Web Text))

Max Activating Token Index: 617

Text #18

Max Range: 3.1274. Min Range: -3.1274

Max Act: 2.0218. Min Act: -0.0000

Data Index: 724003 (C4 (Web Text))

Max Activating Token Index: 545

Text #19

Max Range: 3.1274. Min Range: -3.1274

Max Act: 2.1303. Min Act: -0.0000

Data Index: 996528 (C4 (Web Text))

Max Activating Token Index: 487