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

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

Neuron 1298 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.2074. Min Act: -0.0001

Data Index: 839156 (C4 (Web Text))

Max Activating Token Index: 227

Text #1

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1719. Min Act: -0.0002

Data Index: 400185 (C4 (Web Text))

Max Activating Token Index: 116

Text #2

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1645. Min Act: -0.0001

Data Index: 1121658 (C4 (Web Text))

Max Activating Token Index: 504

Text #3

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1595. Min Act: -0.0001

Data Index: 235647 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1709. Min Act: -0.0001

Data Index: 1299833 (C4 (Web Text))

Max Activating Token Index: 24

Text #5

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1582. Min Act: -0.0001

Data Index: 1235797 (C4 (Web Text))

Max Activating Token Index: 595

Text #6

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1372. Min Act: -0.0001

Data Index: 856764 (C4 (Web Text))

Max Activating Token Index: 71

Text #7

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1520. Min Act: -0.0001

Data Index: 1201049 (C4 (Web Text))

Max Activating Token Index: 544

Text #8

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1452. Min Act: -0.0001

Data Index: 525722 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1537. Min Act: -0.0001

Data Index: 1201614 (C4 (Web Text))

Max Activating Token Index: 216

Text #10

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1472. Min Act: -0.0001

Data Index: 766569 (C4 (Web Text))

Max Activating Token Index: 960

Text #11

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1593. Min Act: -0.0001

Data Index: 1322694 (C4 (Web Text))

Max Activating Token Index: 324

Text #12

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1240. Min Act: -0.0001

Data Index: 205723 (C4 (Web Text))

Max Activating Token Index: 896

Text #13

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1098. Min Act: -0.0001

Data Index: 691381 (C4 (Web Text))

Max Activating Token Index: 872

Text #14

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1397. Min Act: -0.0001

Data Index: 601047 (C4 (Web Text))

Max Activating Token Index: 107

Text #15

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1374. Min Act: -0.0001

Data Index: 195786 (C4 (Web Text))

Max Activating Token Index: 156

Text #16

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1394. Min Act: -0.0001

Data Index: 242942 (C4 (Web Text))

Max Activating Token Index: 406

Text #17

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1350. Min Act: -0.0001

Data Index: 79430 (C4 (Web Text))

Max Activating Token Index: 98

Text #18

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1196. Min Act: -0.0001

Data Index: 108636 (C4 (Web Text))

Max Activating Token Index: 843

Text #19

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1383. Min Act: -0.0001

Data Index: 158753 (C4 (Web Text))

Max Activating Token Index: 397