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

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

Neuron 3796 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2567. Min Act: -0.0002

Data Index: 918252 (C4 (Web Text))

Max Activating Token Index: 715

Text #1

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2278. Min Act: -0.0002

Data Index: 1254399 (C4 (Web Text))

Max Activating Token Index: 540

Text #2

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2110. Min Act: -0.0002

Data Index: 1118163 (C4 (Web Text))

Max Activating Token Index: 807

Text #3

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2008. Min Act: -0.0002

Data Index: 224160 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1867. Min Act: -0.0002

Data Index: 154136 (C4 (Web Text))

Max Activating Token Index: 199

Text #5

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1802. Min Act: -0.0002

Data Index: 708752 (C4 (Web Text))

Max Activating Token Index: 610

Text #6

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1648. Min Act: -0.0002

Data Index: 481236 (C4 (Web Text))

Max Activating Token Index: 358

Text #7

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1622. Min Act: -0.0002

Data Index: 1105641 (C4 (Web Text))

Max Activating Token Index: 669

Text #8

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1540. Min Act: -0.0002

Data Index: 1234671 (C4 (Web Text))

Max Activating Token Index: 625

Text #9

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1479. Min Act: -0.0002

Data Index: 891009 (C4 (Web Text))

Max Activating Token Index: 784

Text #10

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1469. Min Act: -0.0002

Data Index: 1225319 (C4 (Web Text))

Max Activating Token Index: 523

Text #11

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1459. Min Act: -0.0002

Data Index: 851123 (C4 (Web Text))

Max Activating Token Index: 850

Text #12

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1454. Min Act: -0.0002

Data Index: 869250 (C4 (Web Text))

Max Activating Token Index: 265

Text #13

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1440. Min Act: -0.0002

Data Index: 1041862 (C4 (Web Text))

Max Activating Token Index: 702

Text #14

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1446. Min Act: -0.0002

Data Index: 410534 (C4 (Web Text))

Max Activating Token Index: 367

Text #15

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1387. Min Act: -0.0002

Data Index: 374219 (C4 (Web Text))

Max Activating Token Index: 976

Text #16

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1418. Min Act: -0.0002

Data Index: 30281 (C4 (Web Text))

Max Activating Token Index: 289

Text #17

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1456. Min Act: -0.0002

Data Index: 1144569 (C4 (Web Text))

Max Activating Token Index: 470

Text #18

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1437. Min Act: -0.0002

Data Index: 603675 (C4 (Web Text))

Max Activating Token Index: 835

Text #19

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1483. Min Act: -0.0002

Data Index: 1044339 (C4 (Web Text))

Max Activating Token Index: 666