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

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

Neuron 4093 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2889. Min Act: -0.0001

Data Index: 227712 (C4 (Web Text))

Max Activating Token Index: 144

Text #1

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2434. Min Act: -0.0001

Data Index: 541817 (C4 (Web Text))

Max Activating Token Index: 726

Text #2

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2168. Min Act: -0.0001

Data Index: 1234580 (C4 (Web Text))

Max Activating Token Index: 229

Text #3

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2290. Min Act: -0.0001

Data Index: 633530 (C4 (Web Text))

Max Activating Token Index: 476

Text #4

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2072. Min Act: -0.0001

Data Index: 1221036 (C4 (Web Text))

Max Activating Token Index: 886

Text #5

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.1868. Min Act: -0.0000

Data Index: 329382 (C4 (Web Text))

Max Activating Token Index: 970

Text #6

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2200. Min Act: -0.0001

Data Index: 1114959 (C4 (Web Text))

Max Activating Token Index: 563

Text #7

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2282. Min Act: -0.0001

Data Index: 221325 (C4 (Web Text))

Max Activating Token Index: 817

Text #8

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.1971. Min Act: -0.0001

Data Index: 1268593 (C4 (Web Text))

Max Activating Token Index: 295

Text #9

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.1894. Min Act: -0.0000

Data Index: 460753 (C4 (Web Text))

Max Activating Token Index: 436

Text #10

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.1841. Min Act: -0.0001

Data Index: 474269 (C4 (Web Text))

Max Activating Token Index: 699

Text #11

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.1992. Min Act: -0.0000

Data Index: 715088 (C4 (Web Text))

Max Activating Token Index: 455

Text #12

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.1717. Min Act: -0.0001

Data Index: 336669 (C4 (Web Text))

Max Activating Token Index: 307

Text #13

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2049. Min Act: -0.0001

Data Index: 844270 (C4 (Web Text))

Max Activating Token Index: 166

Text #14

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.1954. Min Act: -0.0001

Data Index: 769574 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2002. Min Act: -0.0001

Data Index: 776924 (C4 (Web Text))

Max Activating Token Index: 31

Text #16

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.1798. Min Act: -0.0001

Data Index: 1200247 (C4 (Web Text))

Max Activating Token Index: 1004

Text #17

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.1908. Min Act: -0.0001

Data Index: 54801 (C4 (Web Text))

Max Activating Token Index: 123

Text #18

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.1765. Min Act: -0.0001

Data Index: 1655074 (Python Code)

Max Activating Token Index: 544

Text #19

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.1838. Min Act: -0.0001

Data Index: 1072181 (C4 (Web Text))

Max Activating Token Index: 666