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

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

Neuron 2604 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: 0.7407. Min Range: -0.7407

Max Act: 0.7328. Min Act: -0.0004

Data Index: 110471 (C4 (Web Text))

Max Activating Token Index: 203

Text #1

Max Range: 0.7407. Min Range: -0.7407

Max Act: 0.7202. Min Act: -0.0004

Data Index: 1307674 (C4 (Web Text))

Max Activating Token Index: 487

Text #2

Max Range: 0.7407. Min Range: -0.7407

Max Act: 0.7407. Min Act: -0.0004

Data Index: 504949 (C4 (Web Text))

Max Activating Token Index: 504

Text #3

Max Range: 0.7407. Min Range: -0.7407

Max Act: 0.6800. Min Act: -0.0004

Data Index: 99552 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 0.7407. Min Range: -0.7407

Max Act: 0.7010. Min Act: -0.0004

Data Index: 968648 (C4 (Web Text))

Max Activating Token Index: 742

Text #5

Max Range: 0.7407. Min Range: -0.7407

Max Act: 0.6975. Min Act: -0.0004

Data Index: 505264 (C4 (Web Text))

Max Activating Token Index: 268

Text #6

Max Range: 0.7407. Min Range: -0.7407

Max Act: 0.7405. Min Act: -0.0004

Data Index: 765474 (C4 (Web Text))

Max Activating Token Index: 547

Text #7

Max Range: 0.7407. Min Range: -0.7407

Max Act: 0.7132. Min Act: -0.0004

Data Index: 187040 (C4 (Web Text))

Max Activating Token Index: 427

Text #8

Max Range: 0.7407. Min Range: -0.7407

Max Act: 0.6398. Min Act: -0.0004

Data Index: 946930 (C4 (Web Text))

Max Activating Token Index: 816

Text #9

Max Range: 0.7407. Min Range: -0.7407

Max Act: 0.6757. Min Act: -0.0004

Data Index: 528953 (C4 (Web Text))

Max Activating Token Index: 458

Text #10

Max Range: 0.7407. Min Range: -0.7407

Max Act: 0.6711. Min Act: -0.0004

Data Index: 1319725 (C4 (Web Text))

Max Activating Token Index: 448

Text #11

Max Range: 0.7407. Min Range: -0.7407

Max Act: 0.6445. Min Act: -0.0004

Data Index: 474621 (C4 (Web Text))

Max Activating Token Index: 119

Text #12

Max Range: 0.7407. Min Range: -0.7407

Max Act: 0.6635. Min Act: -0.0004

Data Index: 999613 (C4 (Web Text))

Max Activating Token Index: 10

Text #13

Max Range: 0.7407. Min Range: -0.7407

Max Act: 0.6844. Min Act: -0.0004

Data Index: 1238185 (C4 (Web Text))

Max Activating Token Index: 214

Text #14

Max Range: 0.7407. Min Range: -0.7407

Max Act: 0.6615. Min Act: -0.0004

Data Index: 721929 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 0.7407. Min Range: -0.7407

Max Act: 0.6332. Min Act: -0.0004

Data Index: 646739 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 0.7407. Min Range: -0.7407

Max Act: 0.6725. Min Act: -0.0004

Data Index: 788454 (C4 (Web Text))

Max Activating Token Index: 568

Text #17

Max Range: 0.7407. Min Range: -0.7407

Max Act: 0.6471. Min Act: -0.0004

Data Index: 536501 (C4 (Web Text))

Max Activating Token Index: 501

Text #18

Max Range: 0.7407. Min Range: -0.7407

Max Act: 0.6481. Min Act: -0.0004

Data Index: 846492 (C4 (Web Text))

Max Activating Token Index: 15

Text #19

Max Range: 0.7407. Min Range: -0.7407

Max Act: 0.6458. Min Act: -0.0004

Data Index: 810439 (C4 (Web Text))

Max Activating Token Index: 499