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

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

Neuron 667 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6979. Min Range: -1.6979

Max Act: 1.6979. Min Act: -0.0001

Data Index: 255923 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 1.6979. Min Range: -1.6979

Max Act: 1.4440. Min Act: -0.0001

Data Index: 211889 (C4 (Web Text))

Max Activating Token Index: 147

Text #2

Max Range: 1.6979. Min Range: -1.6979

Max Act: 1.1996. Min Act: -0.0001

Data Index: 337789 (C4 (Web Text))

Max Activating Token Index: 278

Text #3

Max Range: 1.6979. Min Range: -1.6979

Max Act: 1.4043. Min Act: -0.0001

Data Index: 1293709 (C4 (Web Text))

Max Activating Token Index: 844

Text #4

Max Range: 1.6979. Min Range: -1.6979

Max Act: 1.2835. Min Act: -0.0001

Data Index: 791549 (C4 (Web Text))

Max Activating Token Index: 24

Text #5

Max Range: 1.6979. Min Range: -1.6979

Max Act: 1.1737. Min Act: -0.0001

Data Index: 991010 (C4 (Web Text))

Max Activating Token Index: 399

Text #6

Max Range: 1.6979. Min Range: -1.6979

Max Act: 1.2073. Min Act: -0.0001

Data Index: 253460 (C4 (Web Text))

Max Activating Token Index: 698

Text #7

Max Range: 1.6979. Min Range: -1.6979

Max Act: 1.1998. Min Act: -0.0001

Data Index: 1350103 (C4 (Web Text))

Max Activating Token Index: 440

Text #8

Max Range: 1.6979. Min Range: -1.6979

Max Act: 1.1608. Min Act: -0.0001

Data Index: 785367 (C4 (Web Text))

Max Activating Token Index: 118

Text #9

Max Range: 1.6979. Min Range: -1.6979

Max Act: 1.2168. Min Act: -0.0001

Data Index: 1008796 (C4 (Web Text))

Max Activating Token Index: 654

Text #10

Max Range: 1.6979. Min Range: -1.6979

Max Act: 1.1894. Min Act: -0.0001

Data Index: 546014 (C4 (Web Text))

Max Activating Token Index: 428

Text #11

Max Range: 1.6979. Min Range: -1.6979

Max Act: 1.1908. Min Act: -0.0001

Data Index: 233734 (C4 (Web Text))

Max Activating Token Index: 668

Text #12

Max Range: 1.6979. Min Range: -1.6979

Max Act: 1.1952. Min Act: -0.0001

Data Index: 261672 (C4 (Web Text))

Max Activating Token Index: 192

Text #13

Max Range: 1.6979. Min Range: -1.6979

Max Act: 1.1531. Min Act: -0.0001

Data Index: 156447 (C4 (Web Text))

Max Activating Token Index: 30

Text #14

Max Range: 1.6979. Min Range: -1.6979

Max Act: 1.1878. Min Act: -0.0001

Data Index: 619449 (C4 (Web Text))

Max Activating Token Index: 68

Text #15

Max Range: 1.6979. Min Range: -1.6979

Max Act: 1.2286. Min Act: -0.0001

Data Index: 148668 (C4 (Web Text))

Max Activating Token Index: 927

Text #16

Max Range: 1.6979. Min Range: -1.6979

Max Act: 1.1790. Min Act: -0.0001

Data Index: 1206917 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 1.6979. Min Range: -1.6979

Max Act: 1.1376. Min Act: -0.0001

Data Index: 315499 (C4 (Web Text))

Max Activating Token Index: 855

Text #18

Max Range: 1.6979. Min Range: -1.6979

Max Act: 1.1275. Min Act: -0.0001

Data Index: 964693 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 1.6979. Min Range: -1.6979

Max Act: 1.1778. Min Act: -0.0001

Data Index: 596725 (C4 (Web Text))

Max Activating Token Index: 178