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

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

Neuron 2653 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: 0.8839. Min Range: -0.8839

Max Act: 0.8839. Min Act: -0.0001

Data Index: 337985 (C4 (Web Text))

Max Activating Token Index: 880

Text #1

Max Range: 0.8839. Min Range: -0.8839

Max Act: 0.8607. Min Act: -0.0000

Data Index: 480945 (C4 (Web Text))

Max Activating Token Index: 980

Text #2

Max Range: 0.8839. Min Range: -0.8839

Max Act: 0.7585. Min Act: -0.0000

Data Index: 1063924 (C4 (Web Text))

Max Activating Token Index: 780

Text #3

Max Range: 0.8839. Min Range: -0.8839

Max Act: 0.8074. Min Act: -0.0001

Data Index: 66678 (C4 (Web Text))

Max Activating Token Index: 384

Text #4

Max Range: 0.8839. Min Range: -0.8839

Max Act: 0.7418. Min Act: -0.0000

Data Index: 1258729 (C4 (Web Text))

Max Activating Token Index: 195

Text #5

Max Range: 0.8839. Min Range: -0.8839

Max Act: 0.7943. Min Act: -0.0000

Data Index: 915385 (C4 (Web Text))

Max Activating Token Index: 823

Text #6

Max Range: 0.8839. Min Range: -0.8839

Max Act: 0.7386. Min Act: -0.0000

Data Index: 561279 (C4 (Web Text))

Max Activating Token Index: 301

Text #7

Max Range: 0.8839. Min Range: -0.8839

Max Act: 0.7506. Min Act: -0.0000

Data Index: 700193 (C4 (Web Text))

Max Activating Token Index: 593

Text #8

Max Range: 0.8839. Min Range: -0.8839

Max Act: 0.7602. Min Act: -0.0001

Data Index: 812591 (C4 (Web Text))

Max Activating Token Index: 136

Text #9

Max Range: 0.8839. Min Range: -0.8839

Max Act: 0.7108. Min Act: -0.0000

Data Index: 699448 (C4 (Web Text))

Max Activating Token Index: 473

Text #10

Max Range: 0.8839. Min Range: -0.8839

Max Act: 0.7405. Min Act: -0.0000

Data Index: 1195993 (C4 (Web Text))

Max Activating Token Index: 734

Text #11

Max Range: 0.8839. Min Range: -0.8839

Max Act: 0.7714. Min Act: -0.0000

Data Index: 921277 (C4 (Web Text))

Max Activating Token Index: 429

Text #12

Max Range: 0.8839. Min Range: -0.8839

Max Act: 0.7278. Min Act: -0.0000

Data Index: 699922 (C4 (Web Text))

Max Activating Token Index: 594

Text #13

Max Range: 0.8839. Min Range: -0.8839

Max Act: 0.6815. Min Act: -0.0000

Data Index: 1272972 (C4 (Web Text))

Max Activating Token Index: 997

Text #14

Max Range: 0.8839. Min Range: -0.8839

Max Act: 0.7214. Min Act: -0.0001

Data Index: 1217513 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 0.8839. Min Range: -0.8839

Max Act: 0.7440. Min Act: -0.0000

Data Index: 1175890 (C4 (Web Text))

Max Activating Token Index: 853

Text #16

Max Range: 0.8839. Min Range: -0.8839

Max Act: 0.7373. Min Act: -0.0000

Data Index: 319337 (C4 (Web Text))

Max Activating Token Index: 314

Text #17

Max Range: 0.8839. Min Range: -0.8839

Max Act: 0.7212. Min Act: -0.0000

Data Index: 1048738 (C4 (Web Text))

Max Activating Token Index: 92

Text #18

Max Range: 0.8839. Min Range: -0.8839

Max Act: 0.7152. Min Act: -0.0001

Data Index: 239583 (C4 (Web Text))

Max Activating Token Index: 791

Text #19

Max Range: 0.8839. Min Range: -0.8839

Max Act: 0.6642. Min Act: -0.0000

Data Index: 313886 (C4 (Web Text))

Max Activating Token Index: 351