Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2693 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6878. Min Range: -0.6878

Max Act: 0.6878. Min Act: -0.0001

Data Index: 889192 (C4 (Web Text))

Max Activating Token Index: 679

Text #1

Max Range: 0.6878. Min Range: -0.6878

Max Act: 0.6380. Min Act: -0.0001

Data Index: 827619 (C4 (Web Text))

Max Activating Token Index: 213

Text #2

Max Range: 0.6878. Min Range: -0.6878

Max Act: 0.6522. Min Act: -0.0001

Data Index: 825046 (C4 (Web Text))

Max Activating Token Index: 710

Text #3

Max Range: 0.6878. Min Range: -0.6878

Max Act: 0.5379. Min Act: -0.0001

Data Index: 655364 (C4 (Web Text))

Max Activating Token Index: 812

Text #4

Max Range: 0.6878. Min Range: -0.6878

Max Act: 0.5676. Min Act: -0.0001

Data Index: 227006 (C4 (Web Text))

Max Activating Token Index: 221

Text #5

Max Range: 0.6878. Min Range: -0.6878

Max Act: 0.5513. Min Act: -0.0001

Data Index: 1273905 (C4 (Web Text))

Max Activating Token Index: 582

Text #6

Max Range: 0.6878. Min Range: -0.6878

Max Act: 0.5425. Min Act: -0.0001

Data Index: 1257120 (C4 (Web Text))

Max Activating Token Index: 910

Text #7

Max Range: 0.6878. Min Range: -0.6878

Max Act: 0.5407. Min Act: -0.0001

Data Index: 145667 (C4 (Web Text))

Max Activating Token Index: 650

Text #8

Max Range: 0.6878. Min Range: -0.6878

Max Act: 0.5403. Min Act: -0.0001

Data Index: 71384 (C4 (Web Text))

Max Activating Token Index: 891

Text #9

Max Range: 0.6878. Min Range: -0.6878

Max Act: 0.5732. Min Act: -0.0001

Data Index: 547671 (C4 (Web Text))

Max Activating Token Index: 797

Text #10

Max Range: 0.6878. Min Range: -0.6878

Max Act: 0.5062. Min Act: -0.0001

Data Index: 942908 (C4 (Web Text))

Max Activating Token Index: 239

Text #11

Max Range: 0.6878. Min Range: -0.6878

Max Act: 0.4987. Min Act: -0.0001

Data Index: 68217 (C4 (Web Text))

Max Activating Token Index: 893

Text #12

Max Range: 0.6878. Min Range: -0.6878

Max Act: 0.5317. Min Act: -0.0001

Data Index: 165440 (C4 (Web Text))

Max Activating Token Index: 980

Text #13

Max Range: 0.6878. Min Range: -0.6878

Max Act: 0.5134. Min Act: -0.0001

Data Index: 918879 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 0.6878. Min Range: -0.6878

Max Act: 0.4849. Min Act: -0.0001

Data Index: 1170027 (C4 (Web Text))

Max Activating Token Index: 897

Text #15

Max Range: 0.6878. Min Range: -0.6878

Max Act: 0.5463. Min Act: -0.0001

Data Index: 718272 (C4 (Web Text))

Max Activating Token Index: 91

Text #16

Max Range: 0.6878. Min Range: -0.6878

Max Act: 0.5088. Min Act: -0.0001

Data Index: 1562097 (Python Code)

Max Activating Token Index: 629

Text #17

Max Range: 0.6878. Min Range: -0.6878

Max Act: 0.5412. Min Act: -0.0001

Data Index: 891315 (C4 (Web Text))

Max Activating Token Index: 876

Text #18

Max Range: 0.6878. Min Range: -0.6878

Max Act: 0.4981. Min Act: -0.0001

Data Index: 132399 (C4 (Web Text))

Max Activating Token Index: 338

Text #19

Max Range: 0.6878. Min Range: -0.6878

Max Act: 0.5162. Min Act: -0.0001

Data Index: 1279412 (C4 (Web Text))

Max Activating Token Index: 838