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

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

Neuron 3281 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: 0.2709. Min Range: -0.2709

Max Act: 0.2597. Min Act: -0.0000

Data Index: 1128498 (C4 (Web Text))

Max Activating Token Index: 881

Text #1

Max Range: 0.2709. Min Range: -0.2709

Max Act: 0.2709. Min Act: -0.0000

Data Index: 125999 (C4 (Web Text))

Max Activating Token Index: 556

Text #2

Max Range: 0.2709. Min Range: -0.2709

Max Act: 0.2690. Min Act: -0.0000

Data Index: 1268222 (C4 (Web Text))

Max Activating Token Index: 411

Text #3

Max Range: 0.2709. Min Range: -0.2709

Max Act: 0.2551. Min Act: -0.0000

Data Index: 176918 (C4 (Web Text))

Max Activating Token Index: 514

Text #4

Max Range: 0.2709. Min Range: -0.2709

Max Act: 0.2391. Min Act: -0.0000

Data Index: 1098918 (C4 (Web Text))

Max Activating Token Index: 291

Text #5

Max Range: 0.2709. Min Range: -0.2709

Max Act: 0.2533. Min Act: -0.0000

Data Index: 865049 (C4 (Web Text))

Max Activating Token Index: 627

Text #6

Max Range: 0.2709. Min Range: -0.2709

Max Act: 0.2409. Min Act: -0.0000

Data Index: 846426 (C4 (Web Text))

Max Activating Token Index: 146

Text #7

Max Range: 0.2709. Min Range: -0.2709

Max Act: 0.2212. Min Act: -0.0000

Data Index: 46494 (C4 (Web Text))

Max Activating Token Index: 793

Text #8

Max Range: 0.2709. Min Range: -0.2709

Max Act: 0.2102. Min Act: -0.0000

Data Index: 294141 (C4 (Web Text))

Max Activating Token Index: 610

Text #9

Max Range: 0.2709. Min Range: -0.2709

Max Act: 0.2011. Min Act: -0.0000

Data Index: 487556 (C4 (Web Text))

Max Activating Token Index: 248

Text #10

Max Range: 0.2709. Min Range: -0.2709

Max Act: 0.1903. Min Act: -0.0000

Data Index: 260963 (C4 (Web Text))

Max Activating Token Index: 330

Text #11

Max Range: 0.2709. Min Range: -0.2709

Max Act: 0.1701. Min Act: -0.0000

Data Index: 846821 (C4 (Web Text))

Max Activating Token Index: 407

Text #12

Max Range: 0.2709. Min Range: -0.2709

Max Act: 0.1815. Min Act: -0.0000

Data Index: 3560 (C4 (Web Text))

Max Activating Token Index: 546

Text #13

Max Range: 0.2709. Min Range: -0.2709

Max Act: 0.1809. Min Act: -0.0000

Data Index: 1351189 (C4 (Web Text))

Max Activating Token Index: 975

Text #14

Max Range: 0.2709. Min Range: -0.2709

Max Act: 0.1669. Min Act: -0.0000

Data Index: 1244676 (C4 (Web Text))

Max Activating Token Index: 886

Text #15

Max Range: 0.2709. Min Range: -0.2709

Max Act: 0.1711. Min Act: -0.0000

Data Index: 285898 (C4 (Web Text))

Max Activating Token Index: 1003

Text #16

Max Range: 0.2709. Min Range: -0.2709

Max Act: 0.1672. Min Act: -0.0000

Data Index: 929274 (C4 (Web Text))

Max Activating Token Index: 671

Text #17

Max Range: 0.2709. Min Range: -0.2709

Max Act: 0.1736. Min Act: -0.0000

Data Index: 1309492 (C4 (Web Text))

Max Activating Token Index: 127

Text #18

Max Range: 0.2709. Min Range: -0.2709

Max Act: 0.1626. Min Act: -0.0000

Data Index: 1301404 (C4 (Web Text))

Max Activating Token Index: 336

Text #19

Max Range: 0.2709. Min Range: -0.2709

Max Act: 0.1569. Min Act: -0.0000

Data Index: 603915 (C4 (Web Text))

Max Activating Token Index: 290