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

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

Neuron 152 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: 2.0320. Min Range: -2.0320

Max Act: 2.0320. Min Act: -0.0000

Data Index: 61663 (C4 (Web Text))

Max Activating Token Index: 157

Text #1

Max Range: 2.0320. Min Range: -2.0320

Max Act: 1.7253. Min Act: -0.0000

Data Index: 774050 (C4 (Web Text))

Max Activating Token Index: 918

Text #2

Max Range: 2.0320. Min Range: -2.0320

Max Act: 1.5261. Min Act: -0.0000

Data Index: 576826 (C4 (Web Text))

Max Activating Token Index: 1008

Text #3

Max Range: 2.0320. Min Range: -2.0320

Max Act: 1.5092. Min Act: -0.0000

Data Index: 892957 (C4 (Web Text))

Max Activating Token Index: 310

Text #4

Max Range: 2.0320. Min Range: -2.0320

Max Act: 1.3439. Min Act: -0.0000

Data Index: 62730 (C4 (Web Text))

Max Activating Token Index: 304

Text #5

Max Range: 2.0320. Min Range: -2.0320

Max Act: 1.4836. Min Act: -0.0000

Data Index: 98434 (C4 (Web Text))

Max Activating Token Index: 801

Text #6

Max Range: 2.0320. Min Range: -2.0320

Max Act: 1.4891. Min Act: -0.0000

Data Index: 1036897 (C4 (Web Text))

Max Activating Token Index: 673

Text #7

Max Range: 2.0320. Min Range: -2.0320

Max Act: 1.4033. Min Act: -0.0000

Data Index: 724653 (C4 (Web Text))

Max Activating Token Index: 272

Text #8

Max Range: 2.0320. Min Range: -2.0320

Max Act: 1.3532. Min Act: -0.0000

Data Index: 1103094 (C4 (Web Text))

Max Activating Token Index: 1007

Text #9

Max Range: 2.0320. Min Range: -2.0320

Max Act: 1.3308. Min Act: -0.0000

Data Index: 919352 (C4 (Web Text))

Max Activating Token Index: 944

Text #10

Max Range: 2.0320. Min Range: -2.0320

Max Act: 1.2052. Min Act: -0.0000

Data Index: 1770 (C4 (Web Text))

Max Activating Token Index: 66

Text #11

Max Range: 2.0320. Min Range: -2.0320

Max Act: 1.2306. Min Act: -0.0000

Data Index: 1090767 (C4 (Web Text))

Max Activating Token Index: 887

Text #12

Max Range: 2.0320. Min Range: -2.0320

Max Act: 1.2090. Min Act: -0.0000

Data Index: 697010 (C4 (Web Text))

Max Activating Token Index: 655

Text #13

Max Range: 2.0320. Min Range: -2.0320

Max Act: 1.1392. Min Act: -0.0000

Data Index: 252280 (C4 (Web Text))

Max Activating Token Index: 844

Text #14

Max Range: 2.0320. Min Range: -2.0320

Max Act: 1.1266. Min Act: -0.0000

Data Index: 249345 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 2.0320. Min Range: -2.0320

Max Act: 1.1329. Min Act: -0.0000

Data Index: 1199759 (C4 (Web Text))

Max Activating Token Index: 298

Text #16

Max Range: 2.0320. Min Range: -2.0320

Max Act: 1.2120. Min Act: -0.0000

Data Index: 33141 (C4 (Web Text))

Max Activating Token Index: 655

Text #17

Max Range: 2.0320. Min Range: -2.0320

Max Act: 1.2511. Min Act: -0.0000

Data Index: 1166344 (C4 (Web Text))

Max Activating Token Index: 971

Text #18

Max Range: 2.0320. Min Range: -2.0320

Max Act: 1.1110. Min Act: -0.0000

Data Index: 758121 (C4 (Web Text))

Max Activating Token Index: 591

Text #19

Max Range: 2.0320. Min Range: -2.0320

Max Act: 1.1598. Min Act: -0.0000

Data Index: 12035 (C4 (Web Text))

Max Activating Token Index: 6