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

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

Neuron 2000 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3909. Min Range: -2.3909

Max Act: 2.3909. Min Act: -0.0000

Data Index: 402247 (C4 (Web Text))

Max Activating Token Index: 984

Text #1

Max Range: 2.3909. Min Range: -2.3909

Max Act: 2.0754. Min Act: -0.0000

Data Index: 660223 (C4 (Web Text))

Max Activating Token Index: 1022

Text #2

Max Range: 2.3909. Min Range: -2.3909

Max Act: 2.1569. Min Act: -0.0000

Data Index: 949170 (C4 (Web Text))

Max Activating Token Index: 951

Text #3

Max Range: 2.3909. Min Range: -2.3909

Max Act: 2.0337. Min Act: -0.0000

Data Index: 847032 (C4 (Web Text))

Max Activating Token Index: 901

Text #4

Max Range: 2.3909. Min Range: -2.3909

Max Act: 1.9312. Min Act: -0.0000

Data Index: 11985 (C4 (Web Text))

Max Activating Token Index: 827

Text #5

Max Range: 2.3909. Min Range: -2.3909

Max Act: 1.8277. Min Act: -0.0000

Data Index: 481357 (C4 (Web Text))

Max Activating Token Index: 545

Text #6

Max Range: 2.3909. Min Range: -2.3909

Max Act: 1.9206. Min Act: -0.0000

Data Index: 917380 (C4 (Web Text))

Max Activating Token Index: 796

Text #7

Max Range: 2.3909. Min Range: -2.3909

Max Act: 2.0012. Min Act: -0.0000

Data Index: 329882 (C4 (Web Text))

Max Activating Token Index: 685

Text #8

Max Range: 2.3909. Min Range: -2.3909

Max Act: 1.8855. Min Act: -0.0000

Data Index: 133274 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 2.3909. Min Range: -2.3909

Max Act: 1.7912. Min Act: -0.0000

Data Index: 40555 (C4 (Web Text))

Max Activating Token Index: 990

Text #10

Max Range: 2.3909. Min Range: -2.3909

Max Act: 1.6635. Min Act: -0.0000

Data Index: 241374 (C4 (Web Text))

Max Activating Token Index: 332

Text #11

Max Range: 2.3909. Min Range: -2.3909

Max Act: 1.6762. Min Act: -0.0000

Data Index: 140505 (C4 (Web Text))

Max Activating Token Index: 744

Text #12

Max Range: 2.3909. Min Range: -2.3909

Max Act: 1.7439. Min Act: -0.0000

Data Index: 247317 (C4 (Web Text))

Max Activating Token Index: 111

Text #13

Max Range: 2.3909. Min Range: -2.3909

Max Act: 1.7159. Min Act: -0.0000

Data Index: 218218 (C4 (Web Text))

Max Activating Token Index: 130

Text #14

Max Range: 2.3909. Min Range: -2.3909

Max Act: 1.7088. Min Act: -0.0000

Data Index: 315489 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 2.3909. Min Range: -2.3909

Max Act: 1.6071. Min Act: -0.0000

Data Index: 594840 (C4 (Web Text))

Max Activating Token Index: 100

Text #16

Max Range: 2.3909. Min Range: -2.3909

Max Act: 1.6779. Min Act: -0.0000

Data Index: 269467 (C4 (Web Text))

Max Activating Token Index: 804

Text #17

Max Range: 2.3909. Min Range: -2.3909

Max Act: 1.6723. Min Act: -0.0000

Data Index: 889315 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 2.3909. Min Range: -2.3909

Max Act: 1.6698. Min Act: -0.0000

Data Index: 696658 (C4 (Web Text))

Max Activating Token Index: 705

Text #19

Max Range: 2.3909. Min Range: -2.3909

Max Act: 1.5593. Min Act: -0.0000

Data Index: 1015232 (C4 (Web Text))

Max Activating Token Index: 786