Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 617 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.1972. Min Act: -0.0004

Data Index: 70386 (C4 (Web Text))

Max Activating Token Index: 585

Text #1

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.2294. Min Act: -0.0004

Data Index: 625567 (C4 (Web Text))

Max Activating Token Index: 95

Text #2

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.1377. Min Act: -0.0004

Data Index: 329747 (C4 (Web Text))

Max Activating Token Index: 610

Text #3

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.1816. Min Act: -0.0004

Data Index: 348380 (C4 (Web Text))

Max Activating Token Index: 549

Text #4

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.1908. Min Act: -0.0004

Data Index: 567344 (C4 (Web Text))

Max Activating Token Index: 660

Text #5

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.2093. Min Act: -0.0004

Data Index: 702619 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.1695. Min Act: -0.0004

Data Index: 1178040 (C4 (Web Text))

Max Activating Token Index: 828

Text #7

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.1921. Min Act: -0.0004

Data Index: 195874 (C4 (Web Text))

Max Activating Token Index: 210

Text #8

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.1766. Min Act: -0.0004

Data Index: 140287 (C4 (Web Text))

Max Activating Token Index: 848

Text #9

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.1969. Min Act: -0.0004

Data Index: 89443 (C4 (Web Text))

Max Activating Token Index: 105

Text #10

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.1458. Min Act: -0.0004

Data Index: 71509 (C4 (Web Text))

Max Activating Token Index: 846

Text #11

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.1864. Min Act: -0.0004

Data Index: 323138 (C4 (Web Text))

Max Activating Token Index: 313

Text #12

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.2312. Min Act: -0.0004

Data Index: 1354809 (C4 (Web Text))

Max Activating Token Index: 625

Text #13

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.1795. Min Act: -0.0004

Data Index: 985153 (C4 (Web Text))

Max Activating Token Index: 47

Text #14

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.1723. Min Act: -0.0004

Data Index: 188603 (C4 (Web Text))

Max Activating Token Index: 693

Text #15

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.1909. Min Act: -0.0004

Data Index: 495420 (C4 (Web Text))

Max Activating Token Index: 729

Text #16

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.1909. Min Act: -0.0004

Data Index: 1289587 (C4 (Web Text))

Max Activating Token Index: 108

Text #17

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.1641. Min Act: -0.0004

Data Index: 1061272 (C4 (Web Text))

Max Activating Token Index: 111

Text #18

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.1811. Min Act: -0.0004

Data Index: 643247 (C4 (Web Text))

Max Activating Token Index: 724

Text #19

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.2006. Min Act: -0.0004

Data Index: 1021797 (C4 (Web Text))

Max Activating Token Index: 96