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

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

Neuron 3370 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5095. Min Range: -2.5095

Max Act: 2.5095. Min Act: -0.0000

Data Index: 589457 (C4 (Web Text))

Max Activating Token Index: 216

Text #1

Max Range: 2.5095. Min Range: -2.5095

Max Act: 2.2209. Min Act: -0.0000

Data Index: 1029291 (C4 (Web Text))

Max Activating Token Index: 466

Text #2

Max Range: 2.5095. Min Range: -2.5095

Max Act: 2.1074. Min Act: -0.0000

Data Index: 274211 (C4 (Web Text))

Max Activating Token Index: 628

Text #3

Max Range: 2.5095. Min Range: -2.5095

Max Act: 2.1134. Min Act: -0.0000

Data Index: 1338472 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 2.5095. Min Range: -2.5095

Max Act: 1.6834. Min Act: -0.0000

Data Index: 620745 (C4 (Web Text))

Max Activating Token Index: 558

Text #5

Max Range: 2.5095. Min Range: -2.5095

Max Act: 1.6222. Min Act: -0.0000

Data Index: 188606 (C4 (Web Text))

Max Activating Token Index: 217

Text #6

Max Range: 2.5095. Min Range: -2.5095

Max Act: 1.7176. Min Act: -0.0000

Data Index: 113697 (C4 (Web Text))

Max Activating Token Index: 421

Text #7

Max Range: 2.5095. Min Range: -2.5095

Max Act: 1.6414. Min Act: -0.0000

Data Index: 984884 (C4 (Web Text))

Max Activating Token Index: 360

Text #8

Max Range: 2.5095. Min Range: -2.5095

Max Act: 1.6353. Min Act: -0.0000

Data Index: 74147 (C4 (Web Text))

Max Activating Token Index: 504

Text #9

Max Range: 2.5095. Min Range: -2.5095

Max Act: 1.7341. Min Act: -0.0000

Data Index: 26045 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 2.5095. Min Range: -2.5095

Max Act: 1.6844. Min Act: -0.0000

Data Index: 1068161 (C4 (Web Text))

Max Activating Token Index: 276

Text #11

Max Range: 2.5095. Min Range: -2.5095

Max Act: 1.6556. Min Act: -0.0000

Data Index: 100432 (C4 (Web Text))

Max Activating Token Index: 899

Text #12

Max Range: 2.5095. Min Range: -2.5095

Max Act: 1.5521. Min Act: -0.0000

Data Index: 1356393 (C4 (Web Text))

Max Activating Token Index: 646

Text #13

Max Range: 2.5095. Min Range: -2.5095

Max Act: 1.6245. Min Act: -0.0000

Data Index: 917745 (C4 (Web Text))

Max Activating Token Index: 314

Text #14

Max Range: 2.5095. Min Range: -2.5095

Max Act: 1.4893. Min Act: -0.0000

Data Index: 560921 (C4 (Web Text))

Max Activating Token Index: 430

Text #15

Max Range: 2.5095. Min Range: -2.5095

Max Act: 1.3874. Min Act: -0.0000

Data Index: 1276205 (C4 (Web Text))

Max Activating Token Index: 136

Text #16

Max Range: 2.5095. Min Range: -2.5095

Max Act: 1.4746. Min Act: -0.0000

Data Index: 55746 (C4 (Web Text))

Max Activating Token Index: 437

Text #17

Max Range: 2.5095. Min Range: -2.5095

Max Act: 1.3793. Min Act: -0.0000

Data Index: 512278 (C4 (Web Text))

Max Activating Token Index: 267

Text #18

Max Range: 2.5095. Min Range: -2.5095

Max Act: 1.4427. Min Act: -0.0000

Data Index: 76894 (C4 (Web Text))

Max Activating Token Index: 500

Text #19

Max Range: 2.5095. Min Range: -2.5095

Max Act: 1.4258. Min Act: -0.0000

Data Index: 760964 (C4 (Web Text))

Max Activating Token Index: 193