Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4472 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.7633. Min Act: -0.0000

Data Index: 146162 (C4 (Web Text))

Max Activating Token Index: 184

Text #1

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.6449. Min Act: -0.0000

Data Index: 469477 (C4 (Web Text))

Max Activating Token Index: 754

Text #2

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.4673. Min Act: -0.0000

Data Index: 80405 (C4 (Web Text))

Max Activating Token Index: 874

Text #3

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.4565. Min Act: -0.0000

Data Index: 975563 (C4 (Web Text))

Max Activating Token Index: 860

Text #4

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.4184. Min Act: -0.0000

Data Index: 532665 (C4 (Web Text))

Max Activating Token Index: 433

Text #5

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.3928. Min Act: -0.0000

Data Index: 356109 (C4 (Web Text))

Max Activating Token Index: 910

Text #6

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.3410. Min Act: -0.0000

Data Index: 419358 (C4 (Web Text))

Max Activating Token Index: 679

Text #7

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.3628. Min Act: -0.0000

Data Index: 225034 (C4 (Web Text))

Max Activating Token Index: 870

Text #8

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.3365. Min Act: -0.0000

Data Index: 93867 (C4 (Web Text))

Max Activating Token Index: 352

Text #9

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.3760. Min Act: -0.0000

Data Index: 743535 (C4 (Web Text))

Max Activating Token Index: 207

Text #10

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.3464. Min Act: -0.0000

Data Index: 569003 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.3345. Min Act: -0.0000

Data Index: 290517 (C4 (Web Text))

Max Activating Token Index: 676

Text #12

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.3200. Min Act: -0.0000

Data Index: 1203547 (C4 (Web Text))

Max Activating Token Index: 771

Text #13

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.3415. Min Act: -0.0000

Data Index: 241931 (C4 (Web Text))

Max Activating Token Index: 62

Text #14

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.3371. Min Act: -0.0000

Data Index: 1253897 (C4 (Web Text))

Max Activating Token Index: 576

Text #15

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.3487. Min Act: -0.0000

Data Index: 539926 (C4 (Web Text))

Max Activating Token Index: 85

Text #16

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.3452. Min Act: -0.0001

Data Index: 676502 (C4 (Web Text))

Max Activating Token Index: 551

Text #17

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.3296. Min Act: -0.0000

Data Index: 34108 (C4 (Web Text))

Max Activating Token Index: 135

Text #18

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.3365. Min Act: -0.0000

Data Index: 830396 (C4 (Web Text))

Max Activating Token Index: 318

Text #19

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.3376. Min Act: -0.0000

Data Index: 1337340 (C4 (Web Text))

Max Activating Token Index: 871