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

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

Neuron 3462 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8023. Min Range: -0.8023

Max Act: 0.7918. Min Act: -0.0000

Data Index: 109558 (C4 (Web Text))

Max Activating Token Index: 789

Text #1

Max Range: 0.8023. Min Range: -0.8023

Max Act: 0.8023. Min Act: -0.0000

Data Index: 143091 (C4 (Web Text))

Max Activating Token Index: 905

Text #2

Max Range: 0.8023. Min Range: -0.8023

Max Act: 0.5819. Min Act: -0.0000

Data Index: 666121 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 0.8023. Min Range: -0.8023

Max Act: 0.6083. Min Act: -0.0000

Data Index: 667734 (C4 (Web Text))

Max Activating Token Index: 78

Text #4

Max Range: 0.8023. Min Range: -0.8023

Max Act: 0.6046. Min Act: -0.0000

Data Index: 1156193 (C4 (Web Text))

Max Activating Token Index: 475

Text #5

Max Range: 0.8023. Min Range: -0.8023

Max Act: 0.6995. Min Act: -0.0000

Data Index: 1343115 (C4 (Web Text))

Max Activating Token Index: 693

Text #6

Max Range: 0.8023. Min Range: -0.8023

Max Act: 0.5584. Min Act: -0.0000

Data Index: 853167 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 0.8023. Min Range: -0.8023

Max Act: 0.5267. Min Act: -0.0000

Data Index: 1252608 (C4 (Web Text))

Max Activating Token Index: 950

Text #8

Max Range: 0.8023. Min Range: -0.8023

Max Act: 0.5215. Min Act: -0.0000

Data Index: 57119 (C4 (Web Text))

Max Activating Token Index: 826

Text #9

Max Range: 0.8023. Min Range: -0.8023

Max Act: 0.5238. Min Act: -0.0000

Data Index: 380034 (C4 (Web Text))

Max Activating Token Index: 544

Text #10

Max Range: 0.8023. Min Range: -0.8023

Max Act: 0.5511. Min Act: -0.0000

Data Index: 813419 (C4 (Web Text))

Max Activating Token Index: 381

Text #11

Max Range: 0.8023. Min Range: -0.8023

Max Act: 0.5879. Min Act: -0.0000

Data Index: 835545 (C4 (Web Text))

Max Activating Token Index: 1001

Text #12

Max Range: 0.8023. Min Range: -0.8023

Max Act: 0.5771. Min Act: -0.0000

Data Index: 792629 (C4 (Web Text))

Max Activating Token Index: 119

Text #13

Max Range: 0.8023. Min Range: -0.8023

Max Act: 0.5513. Min Act: -0.0000

Data Index: 711159 (C4 (Web Text))

Max Activating Token Index: 341

Text #14

Max Range: 0.8023. Min Range: -0.8023

Max Act: 0.5350. Min Act: -0.0000

Data Index: 1110059 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 0.8023. Min Range: -0.8023

Max Act: 0.5278. Min Act: -0.0000

Data Index: 1568571 (Python Code)

Max Activating Token Index: 538

Text #16

Max Range: 0.8023. Min Range: -0.8023

Max Act: 0.4580. Min Act: -0.0000

Data Index: 621846 (C4 (Web Text))

Max Activating Token Index: 447

Text #17

Max Range: 0.8023. Min Range: -0.8023

Max Act: 0.5431. Min Act: -0.0000

Data Index: 865217 (C4 (Web Text))

Max Activating Token Index: 669

Text #18

Max Range: 0.8023. Min Range: -0.8023

Max Act: 0.5748. Min Act: -0.0000

Data Index: 1208891 (C4 (Web Text))

Max Activating Token Index: 546

Text #19

Max Range: 0.8023. Min Range: -0.8023

Max Act: 0.4255. Min Act: -0.0000

Data Index: 508009 (C4 (Web Text))

Max Activating Token Index: 476