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

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

Neuron 4390 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.8928. Min Range: -8.8928

Max Act: 8.8928. Min Act: -0.0000

Data Index: 1284610 (C4 (Web Text))

Max Activating Token Index: 135

Text #1

Max Range: 8.8928. Min Range: -8.8928

Max Act: 8.7342. Min Act: -0.0000

Data Index: 131346 (C4 (Web Text))

Max Activating Token Index: 570

Text #2

Max Range: 8.8928. Min Range: -8.8928

Max Act: 8.1595. Min Act: -0.0000

Data Index: 312210 (C4 (Web Text))

Max Activating Token Index: 632

Text #3

Max Range: 8.8928. Min Range: -8.8928

Max Act: 8.1745. Min Act: -0.0001

Data Index: 182951 (C4 (Web Text))

Max Activating Token Index: 637

Text #4

Max Range: 8.8928. Min Range: -8.8928

Max Act: 7.6725. Min Act: -0.0000

Data Index: 532660 (C4 (Web Text))

Max Activating Token Index: 1011

Text #5

Max Range: 8.8928. Min Range: -8.8928

Max Act: 7.8378. Min Act: -0.0000

Data Index: 82580 (C4 (Web Text))

Max Activating Token Index: 531

Text #6

Max Range: 8.8928. Min Range: -8.8928

Max Act: 7.6495. Min Act: -0.0000

Data Index: 937584 (C4 (Web Text))

Max Activating Token Index: 504

Text #7

Max Range: 8.8928. Min Range: -8.8928

Max Act: 7.6245. Min Act: -0.0000

Data Index: 129008 (C4 (Web Text))

Max Activating Token Index: 824

Text #8

Max Range: 8.8928. Min Range: -8.8928

Max Act: 7.7522. Min Act: -0.0000

Data Index: 721942 (C4 (Web Text))

Max Activating Token Index: 501

Text #9

Max Range: 8.8928. Min Range: -8.8928

Max Act: 7.0398. Min Act: -0.0000

Data Index: 1277689 (C4 (Web Text))

Max Activating Token Index: 1004

Text #10

Max Range: 8.8928. Min Range: -8.8928

Max Act: 7.0853. Min Act: -0.0000

Data Index: 531025 (C4 (Web Text))

Max Activating Token Index: 446

Text #11

Max Range: 8.8928. Min Range: -8.8928

Max Act: 7.1933. Min Act: -0.0000

Data Index: 516789 (C4 (Web Text))

Max Activating Token Index: 179

Text #12

Max Range: 8.8928. Min Range: -8.8928

Max Act: 7.1820. Min Act: -0.0000

Data Index: 566928 (C4 (Web Text))

Max Activating Token Index: 455

Text #13

Max Range: 8.8928. Min Range: -8.8928

Max Act: 7.0464. Min Act: -0.0000

Data Index: 149130 (C4 (Web Text))

Max Activating Token Index: 198

Text #14

Max Range: 8.8928. Min Range: -8.8928

Max Act: 6.5108. Min Act: -0.0000

Data Index: 276811 (C4 (Web Text))

Max Activating Token Index: 346

Text #15

Max Range: 8.8928. Min Range: -8.8928

Max Act: 6.8728. Min Act: -0.0000

Data Index: 1198176 (C4 (Web Text))

Max Activating Token Index: 425

Text #16

Max Range: 8.8928. Min Range: -8.8928

Max Act: 6.5516. Min Act: -0.0000

Data Index: 774899 (C4 (Web Text))

Max Activating Token Index: 185

Text #17

Max Range: 8.8928. Min Range: -8.8928

Max Act: 6.8722. Min Act: -0.0000

Data Index: 801962 (C4 (Web Text))

Max Activating Token Index: 319

Text #18

Max Range: 8.8928. Min Range: -8.8928

Max Act: 6.6948. Min Act: -0.0000

Data Index: 337486 (C4 (Web Text))

Max Activating Token Index: 394

Text #19

Max Range: 8.8928. Min Range: -8.8928

Max Act: 6.4173. Min Act: -0.0000

Data Index: 1324558 (C4 (Web Text))

Max Activating Token Index: 195