Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1120 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0852. Min Range: -2.0852

Max Act: 2.0852. Min Act: -0.0000

Data Index: 125285 (C4 (Web Text))

Max Activating Token Index: 219

Text #1

Max Range: 2.0852. Min Range: -2.0852

Max Act: 1.4783. Min Act: -0.0000

Data Index: 830628 (C4 (Web Text))

Max Activating Token Index: 748

Text #2

Max Range: 2.0852. Min Range: -2.0852

Max Act: 1.3802. Min Act: -0.0000

Data Index: 927410 (C4 (Web Text))

Max Activating Token Index: 500

Text #3

Max Range: 2.0852. Min Range: -2.0852

Max Act: 1.3405. Min Act: -0.0000

Data Index: 1186160 (C4 (Web Text))

Max Activating Token Index: 229

Text #4

Max Range: 2.0852. Min Range: -2.0852

Max Act: 1.3419. Min Act: -0.0000

Data Index: 372507 (C4 (Web Text))

Max Activating Token Index: 204

Text #5

Max Range: 2.0852. Min Range: -2.0852

Max Act: 1.2970. Min Act: -0.0000

Data Index: 585951 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 2.0852. Min Range: -2.0852

Max Act: 1.3365. Min Act: -0.0000

Data Index: 405397 (C4 (Web Text))

Max Activating Token Index: 758

Text #7

Max Range: 2.0852. Min Range: -2.0852

Max Act: 1.2279. Min Act: -0.0000

Data Index: 1168967 (C4 (Web Text))

Max Activating Token Index: 798

Text #8

Max Range: 2.0852. Min Range: -2.0852

Max Act: 1.2255. Min Act: -0.0000

Data Index: 607753 (C4 (Web Text))

Max Activating Token Index: 1002

Text #9

Max Range: 2.0852. Min Range: -2.0852

Max Act: 1.1991. Min Act: -0.0000

Data Index: 923084 (C4 (Web Text))

Max Activating Token Index: 624

Text #10

Max Range: 2.0852. Min Range: -2.0852

Max Act: 1.2498. Min Act: -0.0000

Data Index: 873509 (C4 (Web Text))

Max Activating Token Index: 942

Text #11

Max Range: 2.0852. Min Range: -2.0852

Max Act: 1.1887. Min Act: -0.0000

Data Index: 431807 (C4 (Web Text))

Max Activating Token Index: 754

Text #12

Max Range: 2.0852. Min Range: -2.0852

Max Act: 1.1778. Min Act: -0.0000

Data Index: 1048780 (C4 (Web Text))

Max Activating Token Index: 680

Text #13

Max Range: 2.0852. Min Range: -2.0852

Max Act: 1.1784. Min Act: -0.0000

Data Index: 1288885 (C4 (Web Text))

Max Activating Token Index: 175

Text #14

Max Range: 2.0852. Min Range: -2.0852

Max Act: 1.0991. Min Act: -0.0000

Data Index: 231011 (C4 (Web Text))

Max Activating Token Index: 914

Text #15

Max Range: 2.0852. Min Range: -2.0852

Max Act: 1.0873. Min Act: -0.0000

Data Index: 980674 (C4 (Web Text))

Max Activating Token Index: 293

Text #16

Max Range: 2.0852. Min Range: -2.0852

Max Act: 1.1510. Min Act: -0.0000

Data Index: 1275620 (C4 (Web Text))

Max Activating Token Index: 116

Text #17

Max Range: 2.0852. Min Range: -2.0852

Max Act: 1.1871. Min Act: -0.0000

Data Index: 727207 (C4 (Web Text))

Max Activating Token Index: 991

Text #18

Max Range: 2.0852. Min Range: -2.0852

Max Act: 1.1218. Min Act: -0.0000

Data Index: 560731 (C4 (Web Text))

Max Activating Token Index: 417

Text #19

Max Range: 2.0852. Min Range: -2.0852

Max Act: 1.1781. Min Act: -0.0000

Data Index: 1036721 (C4 (Web Text))

Max Activating Token Index: 189