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

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

Neuron 547 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9264. Min Range: -0.9264

Max Act: 0.8778. Min Act: -0.0000

Data Index: 1409773 (Python Code)

Max Activating Token Index: 950

Text #1

Max Range: 0.9264. Min Range: -0.9264

Max Act: 0.9264. Min Act: -0.0000

Data Index: 1023099 (C4 (Web Text))

Max Activating Token Index: 455

Text #2

Max Range: 0.9264. Min Range: -0.9264

Max Act: 0.8633. Min Act: -0.0000

Data Index: 354257 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 0.9264. Min Range: -0.9264

Max Act: 0.7932. Min Act: -0.0000

Data Index: 1157802 (C4 (Web Text))

Max Activating Token Index: 262

Text #4

Max Range: 0.9264. Min Range: -0.9264

Max Act: 0.7770. Min Act: -0.0000

Data Index: 982089 (C4 (Web Text))

Max Activating Token Index: 904

Text #5

Max Range: 0.9264. Min Range: -0.9264

Max Act: 0.7724. Min Act: -0.0000

Data Index: 1256302 (C4 (Web Text))

Max Activating Token Index: 731

Text #6

Max Range: 0.9264. Min Range: -0.9264

Max Act: 0.7261. Min Act: -0.0000

Data Index: 993811 (C4 (Web Text))

Max Activating Token Index: 392

Text #7

Max Range: 0.9264. Min Range: -0.9264

Max Act: 0.7669. Min Act: -0.0000

Data Index: 1082695 (C4 (Web Text))

Max Activating Token Index: 465

Text #8

Max Range: 0.9264. Min Range: -0.9264

Max Act: 0.7375. Min Act: -0.0000

Data Index: 275971 (C4 (Web Text))

Max Activating Token Index: 580

Text #9

Max Range: 0.9264. Min Range: -0.9264

Max Act: 0.7142. Min Act: -0.0000

Data Index: 1232944 (C4 (Web Text))

Max Activating Token Index: 816

Text #10

Max Range: 0.9264. Min Range: -0.9264

Max Act: 0.7747. Min Act: -0.0000

Data Index: 10293 (C4 (Web Text))

Max Activating Token Index: 711

Text #11

Max Range: 0.9264. Min Range: -0.9264

Max Act: 0.7595. Min Act: -0.0000

Data Index: 904370 (C4 (Web Text))

Max Activating Token Index: 310

Text #12

Max Range: 0.9264. Min Range: -0.9264

Max Act: 0.7253. Min Act: -0.0000

Data Index: 73841 (C4 (Web Text))

Max Activating Token Index: 546

Text #13

Max Range: 0.9264. Min Range: -0.9264

Max Act: 0.6945. Min Act: -0.0000

Data Index: 686341 (C4 (Web Text))

Max Activating Token Index: 41

Text #14

Max Range: 0.9264. Min Range: -0.9264

Max Act: 0.6656. Min Act: -0.0000

Data Index: 43353 (C4 (Web Text))

Max Activating Token Index: 315

Text #15

Max Range: 0.9264. Min Range: -0.9264

Max Act: 0.6812. Min Act: -0.0000

Data Index: 448759 (C4 (Web Text))

Max Activating Token Index: 591

Text #16

Max Range: 0.9264. Min Range: -0.9264

Max Act: 0.6741. Min Act: -0.0000

Data Index: 1359654 (C4 (Web Text))

Max Activating Token Index: 391

Text #17

Max Range: 0.9264. Min Range: -0.9264

Max Act: 0.6483. Min Act: -0.0000

Data Index: 558871 (C4 (Web Text))

Max Activating Token Index: 960

Text #18

Max Range: 0.9264. Min Range: -0.9264

Max Act: 0.6377. Min Act: -0.0000

Data Index: 870912 (C4 (Web Text))

Max Activating Token Index: 409

Text #19

Max Range: 0.9264. Min Range: -0.9264

Max Act: 0.6461. Min Act: -0.0000

Data Index: 1421835 (Python Code)

Max Activating Token Index: 944