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

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

Neuron 4989 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: 2.1918. Min Range: -2.1918

Max Act: 2.1918. Min Act: -0.0000

Data Index: 1041862 (C4 (Web Text))

Max Activating Token Index: 659

Text #1

Max Range: 2.1918. Min Range: -2.1918

Max Act: 1.7201. Min Act: -0.0000

Data Index: 1079957 (C4 (Web Text))

Max Activating Token Index: 61

Text #2

Max Range: 2.1918. Min Range: -2.1918

Max Act: 1.5408. Min Act: -0.0000

Data Index: 724041 (C4 (Web Text))

Max Activating Token Index: 393

Text #3

Max Range: 2.1918. Min Range: -2.1918

Max Act: 1.4905. Min Act: -0.0000

Data Index: 590561 (C4 (Web Text))

Max Activating Token Index: 635

Text #4

Max Range: 2.1918. Min Range: -2.1918

Max Act: 1.4826. Min Act: -0.0000

Data Index: 9547 (C4 (Web Text))

Max Activating Token Index: 951

Text #5

Max Range: 2.1918. Min Range: -2.1918

Max Act: 1.4650. Min Act: -0.0000

Data Index: 404570 (C4 (Web Text))

Max Activating Token Index: 149

Text #6

Max Range: 2.1918. Min Range: -2.1918

Max Act: 1.5391. Min Act: -0.0000

Data Index: 649555 (C4 (Web Text))

Max Activating Token Index: 438

Text #7

Max Range: 2.1918. Min Range: -2.1918

Max Act: 1.5353. Min Act: -0.0000

Data Index: 583592 (C4 (Web Text))

Max Activating Token Index: 605

Text #8

Max Range: 2.1918. Min Range: -2.1918

Max Act: 1.4317. Min Act: -0.0000

Data Index: 1654509 (Python Code)

Max Activating Token Index: 291

Text #9

Max Range: 2.1918. Min Range: -2.1918

Max Act: 1.4855. Min Act: -0.0000

Data Index: 337946 (C4 (Web Text))

Max Activating Token Index: 785

Text #10

Max Range: 2.1918. Min Range: -2.1918

Max Act: 1.3678. Min Act: -0.0000

Data Index: 530732 (C4 (Web Text))

Max Activating Token Index: 580

Text #11

Max Range: 2.1918. Min Range: -2.1918

Max Act: 1.3722. Min Act: -0.0000

Data Index: 799681 (C4 (Web Text))

Max Activating Token Index: 115

Text #12

Max Range: 2.1918. Min Range: -2.1918

Max Act: 1.2873. Min Act: -0.0000

Data Index: 919573 (C4 (Web Text))

Max Activating Token Index: 128

Text #13

Max Range: 2.1918. Min Range: -2.1918

Max Act: 1.3584. Min Act: -0.0000

Data Index: 477336 (C4 (Web Text))

Max Activating Token Index: 654

Text #14

Max Range: 2.1918. Min Range: -2.1918

Max Act: 1.3347. Min Act: -0.0000

Data Index: 734429 (C4 (Web Text))

Max Activating Token Index: 377

Text #15

Max Range: 2.1918. Min Range: -2.1918

Max Act: 1.4169. Min Act: -0.0000

Data Index: 1448717 (Python Code)

Max Activating Token Index: 241

Text #16

Max Range: 2.1918. Min Range: -2.1918

Max Act: 1.2579. Min Act: -0.0000

Data Index: 255758 (C4 (Web Text))

Max Activating Token Index: 800

Text #17

Max Range: 2.1918. Min Range: -2.1918

Max Act: 1.4793. Min Act: -0.0000

Data Index: 653194 (C4 (Web Text))

Max Activating Token Index: 919

Text #18

Max Range: 2.1918. Min Range: -2.1918

Max Act: 1.3044. Min Act: -0.0000

Data Index: 605664 (C4 (Web Text))

Max Activating Token Index: 792

Text #19

Max Range: 2.1918. Min Range: -2.1918

Max Act: 1.2965. Min Act: -0.0000

Data Index: 278079 (C4 (Web Text))

Max Activating Token Index: 532