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

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

Neuron 2254 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4191. Min Range: -1.4191

Max Act: 1.4191. Min Act: -0.0000

Data Index: 211983 (C4 (Web Text))

Max Activating Token Index: 122

Text #1

Max Range: 1.4191. Min Range: -1.4191

Max Act: 0.9776. Min Act: -0.0000

Data Index: 80222 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 1.4191. Min Range: -1.4191

Max Act: 1.0030. Min Act: -0.0000

Data Index: 351958 (C4 (Web Text))

Max Activating Token Index: 973

Text #3

Max Range: 1.4191. Min Range: -1.4191

Max Act: 0.9792. Min Act: -0.0000

Data Index: 579008 (C4 (Web Text))

Max Activating Token Index: 266

Text #4

Max Range: 1.4191. Min Range: -1.4191

Max Act: 0.9535. Min Act: -0.0000

Data Index: 1352341 (C4 (Web Text))

Max Activating Token Index: 607

Text #5

Max Range: 1.4191. Min Range: -1.4191

Max Act: 0.8341. Min Act: 0.0000

Data Index: 32128 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 1.4191. Min Range: -1.4191

Max Act: 0.8583. Min Act: -0.0000

Data Index: 1251837 (C4 (Web Text))

Max Activating Token Index: 572

Text #7

Max Range: 1.4191. Min Range: -1.4191

Max Act: 0.9135. Min Act: -0.0000

Data Index: 1228814 (C4 (Web Text))

Max Activating Token Index: 775

Text #8

Max Range: 1.4191. Min Range: -1.4191

Max Act: 0.8749. Min Act: -0.0000

Data Index: 74730 (C4 (Web Text))

Max Activating Token Index: 638

Text #9

Max Range: 1.4191. Min Range: -1.4191

Max Act: 0.8061. Min Act: -0.0000

Data Index: 628566 (C4 (Web Text))

Max Activating Token Index: 51

Text #10

Max Range: 1.4191. Min Range: -1.4191

Max Act: 0.8145. Min Act: -0.0000

Data Index: 680585 (C4 (Web Text))

Max Activating Token Index: 776

Text #11

Max Range: 1.4191. Min Range: -1.4191

Max Act: 0.8110. Min Act: -0.0000

Data Index: 24631 (C4 (Web Text))

Max Activating Token Index: 85

Text #12

Max Range: 1.4191. Min Range: -1.4191

Max Act: 0.8120. Min Act: -0.0000

Data Index: 271068 (C4 (Web Text))

Max Activating Token Index: 393

Text #13

Max Range: 1.4191. Min Range: -1.4191

Max Act: 0.8166. Min Act: -0.0000

Data Index: 699757 (C4 (Web Text))

Max Activating Token Index: 546

Text #14

Max Range: 1.4191. Min Range: -1.4191

Max Act: 0.8064. Min Act: -0.0000

Data Index: 152702 (C4 (Web Text))

Max Activating Token Index: 190

Text #15

Max Range: 1.4191. Min Range: -1.4191

Max Act: 0.7765. Min Act: -0.0000

Data Index: 289058 (C4 (Web Text))

Max Activating Token Index: 678

Text #16

Max Range: 1.4191. Min Range: -1.4191

Max Act: 0.8111. Min Act: -0.0000

Data Index: 58973 (C4 (Web Text))

Max Activating Token Index: 26

Text #17

Max Range: 1.4191. Min Range: -1.4191

Max Act: 0.7563. Min Act: -0.0000

Data Index: 1100649 (C4 (Web Text))

Max Activating Token Index: 963

Text #18

Max Range: 1.4191. Min Range: -1.4191

Max Act: 0.7756. Min Act: -0.0000

Data Index: 457603 (C4 (Web Text))

Max Activating Token Index: 898

Text #19

Max Range: 1.4191. Min Range: -1.4191

Max Act: 0.7670. Min Act: -0.0000

Data Index: 653427 (C4 (Web Text))

Max Activating Token Index: 294