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

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

Neuron 4466 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1433. Min Range: -3.1433

Max Act: 3.1433. Min Act: -0.0000

Data Index: 761487 (C4 (Web Text))

Max Activating Token Index: 168

Text #1

Max Range: 3.1433. Min Range: -3.1433

Max Act: 2.7415. Min Act: -0.0000

Data Index: 374574 (C4 (Web Text))

Max Activating Token Index: 779

Text #2

Max Range: 3.1433. Min Range: -3.1433

Max Act: 2.7376. Min Act: -0.0000

Data Index: 797222 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 3.1433. Min Range: -3.1433

Max Act: 2.5762. Min Act: -0.0000

Data Index: 533626 (C4 (Web Text))

Max Activating Token Index: 11

Text #4

Max Range: 3.1433. Min Range: -3.1433

Max Act: 2.6683. Min Act: -0.0000

Data Index: 851910 (C4 (Web Text))

Max Activating Token Index: 259

Text #5

Max Range: 3.1433. Min Range: -3.1433

Max Act: 2.6408. Min Act: -0.0000

Data Index: 365076 (C4 (Web Text))

Max Activating Token Index: 596

Text #6

Max Range: 3.1433. Min Range: -3.1433

Max Act: 2.4157. Min Act: -0.0000

Data Index: 693265 (C4 (Web Text))

Max Activating Token Index: 948

Text #7

Max Range: 3.1433. Min Range: -3.1433

Max Act: 2.4238. Min Act: -0.0000

Data Index: 317150 (C4 (Web Text))

Max Activating Token Index: 514

Text #8

Max Range: 3.1433. Min Range: -3.1433

Max Act: 2.3020. Min Act: -0.0000

Data Index: 199506 (C4 (Web Text))

Max Activating Token Index: 409

Text #9

Max Range: 3.1433. Min Range: -3.1433

Max Act: 2.4117. Min Act: -0.0000

Data Index: 1069252 (C4 (Web Text))

Max Activating Token Index: 436

Text #10

Max Range: 3.1433. Min Range: -3.1433

Max Act: 2.3896. Min Act: -0.0000

Data Index: 1025389 (C4 (Web Text))

Max Activating Token Index: 544

Text #11

Max Range: 3.1433. Min Range: -3.1433

Max Act: 2.2685. Min Act: -0.0000

Data Index: 301012 (C4 (Web Text))

Max Activating Token Index: 980

Text #12

Max Range: 3.1433. Min Range: -3.1433

Max Act: 2.1916. Min Act: -0.0000

Data Index: 787031 (C4 (Web Text))

Max Activating Token Index: 5

Text #13

Max Range: 3.1433. Min Range: -3.1433

Max Act: 2.1958. Min Act: -0.0000

Data Index: 1354783 (C4 (Web Text))

Max Activating Token Index: 852

Text #14

Max Range: 3.1433. Min Range: -3.1433

Max Act: 2.3054. Min Act: -0.0000

Data Index: 1108998 (C4 (Web Text))

Max Activating Token Index: 704

Text #15

Max Range: 3.1433. Min Range: -3.1433

Max Act: 2.3038. Min Act: -0.0000

Data Index: 153723 (C4 (Web Text))

Max Activating Token Index: 974

Text #16

Max Range: 3.1433. Min Range: -3.1433

Max Act: 2.2733. Min Act: -0.0000

Data Index: 452819 (C4 (Web Text))

Max Activating Token Index: 930

Text #17

Max Range: 3.1433. Min Range: -3.1433

Max Act: 2.2764. Min Act: -0.0000

Data Index: 285162 (C4 (Web Text))

Max Activating Token Index: 333

Text #18

Max Range: 3.1433. Min Range: -3.1433

Max Act: 2.1427. Min Act: -0.0000

Data Index: 251495 (C4 (Web Text))

Max Activating Token Index: 868

Text #19

Max Range: 3.1433. Min Range: -3.1433

Max Act: 2.1447. Min Act: -0.0000

Data Index: 429550 (C4 (Web Text))

Max Activating Token Index: 438