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

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

Neuron 3540 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: 0.2446. Min Range: -0.2446

Max Act: 0.2423. Min Act: -0.0000

Data Index: 97418 (C4 (Web Text))

Max Activating Token Index: 557

Text #1

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.2446. Min Act: -0.0000

Data Index: 812808 (C4 (Web Text))

Max Activating Token Index: 357

Text #2

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.2197. Min Act: -0.0000

Data Index: 419418 (C4 (Web Text))

Max Activating Token Index: 496

Text #3

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1985. Min Act: -0.0000

Data Index: 1337981 (C4 (Web Text))

Max Activating Token Index: 456

Text #4

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1960. Min Act: -0.0000

Data Index: 1218413 (C4 (Web Text))

Max Activating Token Index: 556

Text #5

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1821. Min Act: -0.0000

Data Index: 1268444 (C4 (Web Text))

Max Activating Token Index: 947

Text #6

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1865. Min Act: -0.0000

Data Index: 125173 (C4 (Web Text))

Max Activating Token Index: 917

Text #7

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1751. Min Act: -0.0000

Data Index: 1339149 (C4 (Web Text))

Max Activating Token Index: 743

Text #8

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1877. Min Act: -0.0000

Data Index: 243054 (C4 (Web Text))

Max Activating Token Index: 619

Text #9

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1726. Min Act: -0.0000

Data Index: 207549 (C4 (Web Text))

Max Activating Token Index: 763

Text #10

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1710. Min Act: -0.0000

Data Index: 708256 (C4 (Web Text))

Max Activating Token Index: 443

Text #11

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1748. Min Act: -0.0000

Data Index: 1195960 (C4 (Web Text))

Max Activating Token Index: 463

Text #12

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1794. Min Act: -0.0000

Data Index: 949705 (C4 (Web Text))

Max Activating Token Index: 1015

Text #13

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1711. Min Act: -0.0000

Data Index: 1050479 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1690. Min Act: -0.0000

Data Index: 276009 (C4 (Web Text))

Max Activating Token Index: 770

Text #15

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1682. Min Act: -0.0000

Data Index: 893007 (C4 (Web Text))

Max Activating Token Index: 56

Text #16

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1664. Min Act: -0.0000

Data Index: 898726 (C4 (Web Text))

Max Activating Token Index: 138

Text #17

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1709. Min Act: -0.0000

Data Index: 413534 (C4 (Web Text))

Max Activating Token Index: 782

Text #18

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1575. Min Act: -0.0000

Data Index: 261915 (C4 (Web Text))

Max Activating Token Index: 330

Text #19

Max Range: 0.2446. Min Range: -0.2446

Max Act: 0.1640. Min Act: -0.0000

Data Index: 1199845 (C4 (Web Text))

Max Activating Token Index: 953