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

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

Neuron 713 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2130. Min Range: -0.2130

Max Act: 0.2130. Min Act: -0.0001

Data Index: 293681 (C4 (Web Text))

Max Activating Token Index: 228

Text #1

Max Range: 0.2130. Min Range: -0.2130

Max Act: 0.2004. Min Act: -0.0001

Data Index: 506911 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 0.2130. Min Range: -0.2130

Max Act: 0.1963. Min Act: -0.0001

Data Index: 690758 (C4 (Web Text))

Max Activating Token Index: 79

Text #3

Max Range: 0.2130. Min Range: -0.2130

Max Act: 0.1861. Min Act: -0.0001

Data Index: 848415 (C4 (Web Text))

Max Activating Token Index: 847

Text #4

Max Range: 0.2130. Min Range: -0.2130

Max Act: 0.1807. Min Act: -0.0001

Data Index: 899021 (C4 (Web Text))

Max Activating Token Index: 583

Text #5

Max Range: 0.2130. Min Range: -0.2130

Max Act: 0.1735. Min Act: -0.0001

Data Index: 739976 (C4 (Web Text))

Max Activating Token Index: 286

Text #6

Max Range: 0.2130. Min Range: -0.2130

Max Act: 0.1891. Min Act: -0.0001

Data Index: 569856 (C4 (Web Text))

Max Activating Token Index: 556

Text #7

Max Range: 0.2130. Min Range: -0.2130

Max Act: 0.1753. Min Act: -0.0001

Data Index: 1107454 (C4 (Web Text))

Max Activating Token Index: 267

Text #8

Max Range: 0.2130. Min Range: -0.2130

Max Act: 0.1608. Min Act: -0.0001

Data Index: 535111 (C4 (Web Text))

Max Activating Token Index: 677

Text #9

Max Range: 0.2130. Min Range: -0.2130

Max Act: 0.1730. Min Act: -0.0001

Data Index: 168989 (C4 (Web Text))

Max Activating Token Index: 832

Text #10

Max Range: 0.2130. Min Range: -0.2130

Max Act: 0.1557. Min Act: -0.0001

Data Index: 1118898 (C4 (Web Text))

Max Activating Token Index: 810

Text #11

Max Range: 0.2130. Min Range: -0.2130

Max Act: 0.1629. Min Act: -0.0001

Data Index: 587861 (C4 (Web Text))

Max Activating Token Index: 606

Text #12

Max Range: 0.2130. Min Range: -0.2130

Max Act: 0.1681. Min Act: -0.0001

Data Index: 1037600 (C4 (Web Text))

Max Activating Token Index: 428

Text #13

Max Range: 0.2130. Min Range: -0.2130

Max Act: 0.1607. Min Act: -0.0001

Data Index: 549300 (C4 (Web Text))

Max Activating Token Index: 932

Text #14

Max Range: 0.2130. Min Range: -0.2130

Max Act: 0.1656. Min Act: -0.0001

Data Index: 777851 (C4 (Web Text))

Max Activating Token Index: 241

Text #15

Max Range: 0.2130. Min Range: -0.2130

Max Act: 0.1444. Min Act: -0.0001

Data Index: 428036 (C4 (Web Text))

Max Activating Token Index: 64

Text #16

Max Range: 0.2130. Min Range: -0.2130

Max Act: 0.1473. Min Act: -0.0001

Data Index: 1194017 (C4 (Web Text))

Max Activating Token Index: 292

Text #17

Max Range: 0.2130. Min Range: -0.2130

Max Act: 0.1543. Min Act: -0.0001

Data Index: 890676 (C4 (Web Text))

Max Activating Token Index: 639

Text #18

Max Range: 0.2130. Min Range: -0.2130

Max Act: 0.1474. Min Act: -0.0001

Data Index: 261919 (C4 (Web Text))

Max Activating Token Index: 565

Text #19

Max Range: 0.2130. Min Range: -0.2130

Max Act: 0.1567. Min Act: -0.0001

Data Index: 1052661 (C4 (Web Text))

Max Activating Token Index: 721