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

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

Neuron 2021 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.8757. Min Act: -0.0001

Data Index: 352943 (C4 (Web Text))

Max Activating Token Index: 353

Text #1

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.8894. Min Act: -0.0001

Data Index: 680393 (C4 (Web Text))

Max Activating Token Index: 532

Text #2

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.8286. Min Act: -0.0001

Data Index: 658312 (C4 (Web Text))

Max Activating Token Index: 292

Text #3

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.7374. Min Act: -0.0001

Data Index: 687554 (C4 (Web Text))

Max Activating Token Index: 275

Text #4

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.7459. Min Act: -0.0001

Data Index: 1078745 (C4 (Web Text))

Max Activating Token Index: 425

Text #5

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.6683. Min Act: -0.0001

Data Index: 377531 (C4 (Web Text))

Max Activating Token Index: 978

Text #6

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.7564. Min Act: -0.0001

Data Index: 1276849 (C4 (Web Text))

Max Activating Token Index: 761

Text #7

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.6675. Min Act: -0.0001

Data Index: 642084 (C4 (Web Text))

Max Activating Token Index: 528

Text #8

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.6220. Min Act: -0.0001

Data Index: 1086279 (C4 (Web Text))

Max Activating Token Index: 385

Text #9

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.6673. Min Act: -0.0001

Data Index: 1173487 (C4 (Web Text))

Max Activating Token Index: 501

Text #10

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.6634. Min Act: -0.0001

Data Index: 1017404 (C4 (Web Text))

Max Activating Token Index: 998

Text #11

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.6330. Min Act: -0.0001

Data Index: 1057454 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.6127. Min Act: -0.0001

Data Index: 1265144 (C4 (Web Text))

Max Activating Token Index: 167

Text #13

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.6102. Min Act: -0.0001

Data Index: 834310 (C4 (Web Text))

Max Activating Token Index: 83

Text #14

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.5471. Min Act: -0.0001

Data Index: 1184643 (C4 (Web Text))

Max Activating Token Index: 179

Text #15

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.5977. Min Act: -0.0001

Data Index: 450197 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.6182. Min Act: -0.0001

Data Index: 8148 (C4 (Web Text))

Max Activating Token Index: 844

Text #17

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.5503. Min Act: -0.0001

Data Index: 625283 (C4 (Web Text))

Max Activating Token Index: 107

Text #18

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.5938. Min Act: -0.0001

Data Index: 217584 (C4 (Web Text))

Max Activating Token Index: 642

Text #19

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.5738. Min Act: -0.0001

Data Index: 473484 (C4 (Web Text))

Max Activating Token Index: 117