Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3868 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0293. Min Range: -1.0293

Max Act: 1.0293. Min Act: -0.0000

Data Index: 818710 (C4 (Web Text))

Max Activating Token Index: 744

Text #1

Max Range: 1.0293. Min Range: -1.0293

Max Act: 0.9391. Min Act: -0.0000

Data Index: 696198 (C4 (Web Text))

Max Activating Token Index: 962

Text #2

Max Range: 1.0293. Min Range: -1.0293

Max Act: 0.9294. Min Act: -0.0001

Data Index: 895415 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 1.0293. Min Range: -1.0293

Max Act: 0.8326. Min Act: -0.0001

Data Index: 533034 (C4 (Web Text))

Max Activating Token Index: 502

Text #4

Max Range: 1.0293. Min Range: -1.0293

Max Act: 0.8248. Min Act: -0.0000

Data Index: 574869 (C4 (Web Text))

Max Activating Token Index: 178

Text #5

Max Range: 1.0293. Min Range: -1.0293

Max Act: 0.8047. Min Act: -0.0001

Data Index: 1017258 (C4 (Web Text))

Max Activating Token Index: 516

Text #6

Max Range: 1.0293. Min Range: -1.0293

Max Act: 0.8438. Min Act: -0.0001

Data Index: 1204071 (C4 (Web Text))

Max Activating Token Index: 916

Text #7

Max Range: 1.0293. Min Range: -1.0293

Max Act: 0.7935. Min Act: -0.0001

Data Index: 1621276 (Python Code)

Max Activating Token Index: 109

Text #8

Max Range: 1.0293. Min Range: -1.0293

Max Act: 0.7808. Min Act: -0.0001

Data Index: 509959 (C4 (Web Text))

Max Activating Token Index: 126

Text #9

Max Range: 1.0293. Min Range: -1.0293

Max Act: 0.8123. Min Act: -0.0000

Data Index: 999993 (C4 (Web Text))

Max Activating Token Index: 264

Text #10

Max Range: 1.0293. Min Range: -1.0293

Max Act: 0.8117. Min Act: -0.0000

Data Index: 1468707 (Python Code)

Max Activating Token Index: 127

Text #11

Max Range: 1.0293. Min Range: -1.0293

Max Act: 0.7658. Min Act: -0.0001

Data Index: 978653 (C4 (Web Text))

Max Activating Token Index: 518

Text #12

Max Range: 1.0293. Min Range: -1.0293

Max Act: 0.7589. Min Act: -0.0000

Data Index: 1158457 (C4 (Web Text))

Max Activating Token Index: 273

Text #13

Max Range: 1.0293. Min Range: -1.0293

Max Act: 0.8341. Min Act: -0.0000

Data Index: 1519563 (Python Code)

Max Activating Token Index: 81

Text #14

Max Range: 1.0293. Min Range: -1.0293

Max Act: 0.7735. Min Act: -0.0000

Data Index: 319500 (C4 (Web Text))

Max Activating Token Index: 859

Text #15

Max Range: 1.0293. Min Range: -1.0293

Max Act: 0.7112. Min Act: -0.0000

Data Index: 388337 (C4 (Web Text))

Max Activating Token Index: 851

Text #16

Max Range: 1.0293. Min Range: -1.0293

Max Act: 0.7485. Min Act: -0.0000

Data Index: 808617 (C4 (Web Text))

Max Activating Token Index: 106

Text #17

Max Range: 1.0293. Min Range: -1.0293

Max Act: 0.7717. Min Act: -0.0000

Data Index: 790072 (C4 (Web Text))

Max Activating Token Index: 364

Text #18

Max Range: 1.0293. Min Range: -1.0293

Max Act: 0.7012. Min Act: -0.0000

Data Index: 18264 (C4 (Web Text))

Max Activating Token Index: 218

Text #19

Max Range: 1.0293. Min Range: -1.0293

Max Act: 0.7468. Min Act: -0.0001

Data Index: 1226166 (C4 (Web Text))

Max Activating Token Index: 363