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

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

Neuron 2512 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7950. Min Range: -0.7950

Max Act: 0.7950. Min Act: -0.0000

Data Index: 376108 (C4 (Web Text))

Max Activating Token Index: 219

Text #1

Max Range: 0.7950. Min Range: -0.7950

Max Act: 0.6253. Min Act: -0.0000

Data Index: 153035 (C4 (Web Text))

Max Activating Token Index: 946

Text #2

Max Range: 0.7950. Min Range: -0.7950

Max Act: 0.6498. Min Act: -0.0000

Data Index: 187419 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 0.7950. Min Range: -0.7950

Max Act: 0.5608. Min Act: -0.0000

Data Index: 851704 (C4 (Web Text))

Max Activating Token Index: 171

Text #4

Max Range: 0.7950. Min Range: -0.7950

Max Act: 0.5483. Min Act: -0.0000

Data Index: 298631 (C4 (Web Text))

Max Activating Token Index: 715

Text #5

Max Range: 0.7950. Min Range: -0.7950

Max Act: 0.5628. Min Act: -0.0000

Data Index: 363805 (C4 (Web Text))

Max Activating Token Index: 131

Text #6

Max Range: 0.7950. Min Range: -0.7950

Max Act: 0.5552. Min Act: -0.0000

Data Index: 542002 (C4 (Web Text))

Max Activating Token Index: 567

Text #7

Max Range: 0.7950. Min Range: -0.7950

Max Act: 0.5242. Min Act: -0.0000

Data Index: 505291 (C4 (Web Text))

Max Activating Token Index: 536

Text #8

Max Range: 0.7950. Min Range: -0.7950

Max Act: 0.5606. Min Act: -0.0000

Data Index: 913313 (C4 (Web Text))

Max Activating Token Index: 906

Text #9

Max Range: 0.7950. Min Range: -0.7950

Max Act: 0.5394. Min Act: -0.0000

Data Index: 1289310 (C4 (Web Text))

Max Activating Token Index: 610

Text #10

Max Range: 0.7950. Min Range: -0.7950

Max Act: 0.5593. Min Act: -0.0001

Data Index: 188298 (C4 (Web Text))

Max Activating Token Index: 738

Text #11

Max Range: 0.7950. Min Range: -0.7950

Max Act: 0.5252. Min Act: -0.0000

Data Index: 82913 (C4 (Web Text))

Max Activating Token Index: 621

Text #12

Max Range: 0.7950. Min Range: -0.7950

Max Act: 0.4993. Min Act: -0.0000

Data Index: 389947 (C4 (Web Text))

Max Activating Token Index: 786

Text #13

Max Range: 0.7950. Min Range: -0.7950

Max Act: 0.5320. Min Act: -0.0000

Data Index: 911879 (C4 (Web Text))

Max Activating Token Index: 411

Text #14

Max Range: 0.7950. Min Range: -0.7950

Max Act: 0.4960. Min Act: 0.0000

Data Index: 28637 (C4 (Web Text))

Max Activating Token Index: 489

Text #15

Max Range: 0.7950. Min Range: -0.7950

Max Act: 0.4944. Min Act: -0.0000

Data Index: 302906 (C4 (Web Text))

Max Activating Token Index: 172

Text #16

Max Range: 0.7950. Min Range: -0.7950

Max Act: 0.4775. Min Act: -0.0000

Data Index: 1018488 (C4 (Web Text))

Max Activating Token Index: 728

Text #17

Max Range: 0.7950. Min Range: -0.7950

Max Act: 0.5073. Min Act: -0.0000

Data Index: 559094 (C4 (Web Text))

Max Activating Token Index: 417

Text #18

Max Range: 0.7950. Min Range: -0.7950

Max Act: 0.5177. Min Act: -0.0000

Data Index: 675688 (C4 (Web Text))

Max Activating Token Index: 837

Text #19

Max Range: 0.7950. Min Range: -0.7950

Max Act: 0.5143. Min Act: -0.0001

Data Index: 207122 (C4 (Web Text))

Max Activating Token Index: 748