Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2174 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.5535. Min Act: -0.0004

Data Index: 865312 (C4 (Web Text))

Max Activating Token Index: 320

Text #1

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.3472. Min Act: -0.0004

Data Index: 302232 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.5734. Min Act: -0.0004

Data Index: 1054475 (C4 (Web Text))

Max Activating Token Index: 530

Text #3

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.6058. Min Act: -0.0004

Data Index: 89381 (C4 (Web Text))

Max Activating Token Index: 109

Text #4

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.5638. Min Act: -0.0004

Data Index: 491278 (C4 (Web Text))

Max Activating Token Index: 707

Text #5

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.5812. Min Act: -0.0004

Data Index: 1044125 (C4 (Web Text))

Max Activating Token Index: 231

Text #6

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.5932. Min Act: -0.0004

Data Index: 1314161 (C4 (Web Text))

Max Activating Token Index: 566

Text #7

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.5478. Min Act: -0.0004

Data Index: 966631 (C4 (Web Text))

Max Activating Token Index: 460

Text #8

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.5601. Min Act: -0.0004

Data Index: 735127 (C4 (Web Text))

Max Activating Token Index: 477

Text #9

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4422. Min Act: -0.0004

Data Index: 1235197 (C4 (Web Text))

Max Activating Token Index: 705

Text #10

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.5191. Min Act: -0.0004

Data Index: 1332687 (C4 (Web Text))

Max Activating Token Index: 639

Text #11

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.5332. Min Act: -0.0004

Data Index: 262566 (C4 (Web Text))

Max Activating Token Index: 787

Text #12

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.5324. Min Act: -0.0004

Data Index: 202429 (C4 (Web Text))

Max Activating Token Index: 676

Text #13

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.5103. Min Act: -0.0004

Data Index: 83648 (C4 (Web Text))

Max Activating Token Index: 25

Text #14

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4885. Min Act: -0.0004

Data Index: 667011 (C4 (Web Text))

Max Activating Token Index: 571

Text #15

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.5196. Min Act: -0.0004

Data Index: 1208842 (C4 (Web Text))

Max Activating Token Index: 219

Text #16

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.5127. Min Act: -0.0004

Data Index: 1110327 (C4 (Web Text))

Max Activating Token Index: 918

Text #17

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.5111. Min Act: -0.0004

Data Index: 523402 (C4 (Web Text))

Max Activating Token Index: 710

Text #18

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4625. Min Act: -0.0004

Data Index: 557004 (C4 (Web Text))

Max Activating Token Index: 628

Text #19

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.3600. Min Act: -0.0004

Data Index: 971934 (C4 (Web Text))

Max Activating Token Index: 853