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

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

Neuron 1893 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8952. Min Range: -2.8952

Max Act: 2.7911. Min Act: -0.0000

Data Index: 1126643 (C4 (Web Text))

Max Activating Token Index: 717

Text #1

Max Range: 2.8952. Min Range: -2.8952

Max Act: 2.8952. Min Act: -0.0000

Data Index: 457966 (C4 (Web Text))

Max Activating Token Index: 901

Text #2

Max Range: 2.8952. Min Range: -2.8952

Max Act: 2.4436. Min Act: -0.0000

Data Index: 690923 (C4 (Web Text))

Max Activating Token Index: 369

Text #3

Max Range: 2.8952. Min Range: -2.8952

Max Act: 2.3807. Min Act: -0.0000

Data Index: 1274786 (C4 (Web Text))

Max Activating Token Index: 527

Text #4

Max Range: 2.8952. Min Range: -2.8952

Max Act: 2.3765. Min Act: -0.0000

Data Index: 45886 (C4 (Web Text))

Max Activating Token Index: 700

Text #5

Max Range: 2.8952. Min Range: -2.8952

Max Act: 2.2294. Min Act: -0.0000

Data Index: 524048 (C4 (Web Text))

Max Activating Token Index: 261

Text #6

Max Range: 2.8952. Min Range: -2.8952

Max Act: 2.3018. Min Act: -0.0000

Data Index: 1112865 (C4 (Web Text))

Max Activating Token Index: 93

Text #7

Max Range: 2.8952. Min Range: -2.8952

Max Act: 2.4215. Min Act: -0.0000

Data Index: 82650 (C4 (Web Text))

Max Activating Token Index: 195

Text #8

Max Range: 2.8952. Min Range: -2.8952

Max Act: 2.0916. Min Act: -0.0000

Data Index: 396635 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 2.8952. Min Range: -2.8952

Max Act: 2.2873. Min Act: -0.0000

Data Index: 49630 (C4 (Web Text))

Max Activating Token Index: 90

Text #10

Max Range: 2.8952. Min Range: -2.8952

Max Act: 2.1246. Min Act: -0.0000

Data Index: 1339760 (C4 (Web Text))

Max Activating Token Index: 154

Text #11

Max Range: 2.8952. Min Range: -2.8952

Max Act: 2.0170. Min Act: -0.0000

Data Index: 438827 (C4 (Web Text))

Max Activating Token Index: 995

Text #12

Max Range: 2.8952. Min Range: -2.8952

Max Act: 2.2010. Min Act: -0.0000

Data Index: 932813 (C4 (Web Text))

Max Activating Token Index: 432

Text #13

Max Range: 2.8952. Min Range: -2.8952

Max Act: 2.0339. Min Act: -0.0000

Data Index: 46528 (C4 (Web Text))

Max Activating Token Index: 725

Text #14

Max Range: 2.8952. Min Range: -2.8952

Max Act: 2.1353. Min Act: -0.0000

Data Index: 1197500 (C4 (Web Text))

Max Activating Token Index: 392

Text #15

Max Range: 2.8952. Min Range: -2.8952

Max Act: 2.2517. Min Act: -0.0000

Data Index: 1172385 (C4 (Web Text))

Max Activating Token Index: 561

Text #16

Max Range: 2.8952. Min Range: -2.8952

Max Act: 2.2184. Min Act: -0.0000

Data Index: 1076959 (C4 (Web Text))

Max Activating Token Index: 123

Text #17

Max Range: 2.8952. Min Range: -2.8952

Max Act: 2.1252. Min Act: -0.0000

Data Index: 43729 (C4 (Web Text))

Max Activating Token Index: 621

Text #18

Max Range: 2.8952. Min Range: -2.8952

Max Act: 1.9969. Min Act: -0.0000

Data Index: 735688 (C4 (Web Text))

Max Activating Token Index: 586

Text #19

Max Range: 2.8952. Min Range: -2.8952

Max Act: 1.9094. Min Act: -0.0000

Data Index: 1256521 (C4 (Web Text))

Max Activating Token Index: 218