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

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

Neuron 3442 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5809. Min Range: -4.5809

Max Act: 4.5809. Min Act: -0.0000

Data Index: 72965 (C4 (Web Text))

Max Activating Token Index: 181

Text #1

Max Range: 4.5809. Min Range: -4.5809

Max Act: 4.5364. Min Act: -0.0000

Data Index: 573164 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 4.5809. Min Range: -4.5809

Max Act: 4.1904. Min Act: -0.0000

Data Index: 835780 (C4 (Web Text))

Max Activating Token Index: 1019

Text #3

Max Range: 4.5809. Min Range: -4.5809

Max Act: 4.1815. Min Act: -0.0000

Data Index: 1022958 (C4 (Web Text))

Max Activating Token Index: 795

Text #4

Max Range: 4.5809. Min Range: -4.5809

Max Act: 4.2866. Min Act: -0.0000

Data Index: 1108562 (C4 (Web Text))

Max Activating Token Index: 528

Text #5

Max Range: 4.5809. Min Range: -4.5809

Max Act: 4.4572. Min Act: -0.0000

Data Index: 1139777 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 4.5809. Min Range: -4.5809

Max Act: 4.2493. Min Act: -0.0000

Data Index: 612335 (C4 (Web Text))

Max Activating Token Index: 391

Text #7

Max Range: 4.5809. Min Range: -4.5809

Max Act: 4.2463. Min Act: -0.0000

Data Index: 372995 (C4 (Web Text))

Max Activating Token Index: 3

Text #8

Max Range: 4.5809. Min Range: -4.5809

Max Act: 4.4056. Min Act: -0.0000

Data Index: 1175985 (C4 (Web Text))

Max Activating Token Index: 664

Text #9

Max Range: 4.5809. Min Range: -4.5809

Max Act: 4.2343. Min Act: -0.0000

Data Index: 371060 (C4 (Web Text))

Max Activating Token Index: 250

Text #10

Max Range: 4.5809. Min Range: -4.5809

Max Act: 4.0920. Min Act: -0.0000

Data Index: 941005 (C4 (Web Text))

Max Activating Token Index: 357

Text #11

Max Range: 4.5809. Min Range: -4.5809

Max Act: 4.2469. Min Act: -0.0000

Data Index: 184363 (C4 (Web Text))

Max Activating Token Index: 684

Text #12

Max Range: 4.5809. Min Range: -4.5809

Max Act: 4.2382. Min Act: -0.0000

Data Index: 665721 (C4 (Web Text))

Max Activating Token Index: 917

Text #13

Max Range: 4.5809. Min Range: -4.5809

Max Act: 4.1980. Min Act: -0.0000

Data Index: 1333831 (C4 (Web Text))

Max Activating Token Index: 820

Text #14

Max Range: 4.5809. Min Range: -4.5809

Max Act: 4.1939. Min Act: -0.0000

Data Index: 1221634 (C4 (Web Text))

Max Activating Token Index: 710

Text #15

Max Range: 4.5809. Min Range: -4.5809

Max Act: 4.3987. Min Act: -0.0000

Data Index: 1399644 (Python Code)

Max Activating Token Index: 496

Text #16

Max Range: 4.5809. Min Range: -4.5809

Max Act: 4.0344. Min Act: -0.0000

Data Index: 758010 (C4 (Web Text))

Max Activating Token Index: 790

Text #17

Max Range: 4.5809. Min Range: -4.5809

Max Act: 4.3252. Min Act: -0.0000

Data Index: 669144 (C4 (Web Text))

Max Activating Token Index: 539

Text #18

Max Range: 4.5809. Min Range: -4.5809

Max Act: 3.9677. Min Act: -0.0000

Data Index: 632284 (C4 (Web Text))

Max Activating Token Index: 864

Text #19

Max Range: 4.5809. Min Range: -4.5809

Max Act: 4.1437. Min Act: -0.0000

Data Index: 702202 (C4 (Web Text))

Max Activating Token Index: 448