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

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

Neuron 744 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2862. Min Act: -0.0001

Data Index: 1328829 (C4 (Web Text))

Max Activating Token Index: 454

Text #1

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2627. Min Act: -0.0000

Data Index: 581531 (C4 (Web Text))

Max Activating Token Index: 980

Text #2

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2375. Min Act: -0.0000

Data Index: 1102024 (C4 (Web Text))

Max Activating Token Index: 930

Text #3

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2346. Min Act: -0.0000

Data Index: 517872 (C4 (Web Text))

Max Activating Token Index: 909

Text #4

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2251. Min Act: -0.0000

Data Index: 250007 (C4 (Web Text))

Max Activating Token Index: 786

Text #5

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2322. Min Act: -0.0001

Data Index: 224348 (C4 (Web Text))

Max Activating Token Index: 914

Text #6

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2299. Min Act: -0.0000

Data Index: 770941 (C4 (Web Text))

Max Activating Token Index: 685

Text #7

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2196. Min Act: -0.0001

Data Index: 199069 (C4 (Web Text))

Max Activating Token Index: 931

Text #8

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2254. Min Act: -0.0001

Data Index: 90872 (C4 (Web Text))

Max Activating Token Index: 57

Text #9

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2218. Min Act: -0.0001

Data Index: 452233 (C4 (Web Text))

Max Activating Token Index: 159

Text #10

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2145. Min Act: -0.0001

Data Index: 81903 (C4 (Web Text))

Max Activating Token Index: 566

Text #11

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2280. Min Act: -0.0000

Data Index: 783730 (C4 (Web Text))

Max Activating Token Index: 739

Text #12

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2196. Min Act: -0.0000

Data Index: 912541 (C4 (Web Text))

Max Activating Token Index: 973

Text #13

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2106. Min Act: -0.0001

Data Index: 391837 (C4 (Web Text))

Max Activating Token Index: 946

Text #14

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2172. Min Act: -0.0001

Data Index: 173301 (C4 (Web Text))

Max Activating Token Index: 122

Text #15

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2095. Min Act: -0.0001

Data Index: 880227 (C4 (Web Text))

Max Activating Token Index: 966

Text #16

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2093. Min Act: -0.0001

Data Index: 470119 (C4 (Web Text))

Max Activating Token Index: 828

Text #17

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2006. Min Act: -0.0000

Data Index: 982851 (C4 (Web Text))

Max Activating Token Index: 1021

Text #18

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2191. Min Act: -0.0000

Data Index: 681584 (C4 (Web Text))

Max Activating Token Index: 192

Text #19

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2030. Min Act: -0.0001

Data Index: 1244471 (C4 (Web Text))

Max Activating Token Index: 874