Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 493 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.8566. Min Act: -0.0001

Data Index: 56998 (C4 (Web Text))

Max Activating Token Index: 617

Text #1

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.8219. Min Act: -0.0001

Data Index: 358323 (C4 (Web Text))

Max Activating Token Index: 592

Text #2

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.7613. Min Act: -0.0001

Data Index: 883651 (C4 (Web Text))

Max Activating Token Index: 3

Text #3

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.7374. Min Act: -0.0001

Data Index: 652764 (C4 (Web Text))

Max Activating Token Index: 138

Text #4

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.7537. Min Act: -0.0001

Data Index: 184371 (C4 (Web Text))

Max Activating Token Index: 253

Text #5

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.6410. Min Act: -0.0001

Data Index: 1008820 (C4 (Web Text))

Max Activating Token Index: 280

Text #6

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.5989. Min Act: -0.0001

Data Index: 1037758 (C4 (Web Text))

Max Activating Token Index: 726

Text #7

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.5915. Min Act: -0.0001

Data Index: 698619 (C4 (Web Text))

Max Activating Token Index: 357

Text #8

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.6096. Min Act: -0.0001

Data Index: 1652978 (Python Code)

Max Activating Token Index: 100

Text #9

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.5119. Min Act: -0.0001

Data Index: 353629 (C4 (Web Text))

Max Activating Token Index: 916

Text #10

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.5733. Min Act: -0.0001

Data Index: 991698 (C4 (Web Text))

Max Activating Token Index: 11

Text #11

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.5663. Min Act: -0.0001

Data Index: 1318408 (C4 (Web Text))

Max Activating Token Index: 137

Text #12

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.5951. Min Act: -0.0001

Data Index: 1215007 (C4 (Web Text))

Max Activating Token Index: 317

Text #13

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.5378. Min Act: -0.0001

Data Index: 626543 (C4 (Web Text))

Max Activating Token Index: 939

Text #14

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.5630. Min Act: -0.0001

Data Index: 939899 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.5180. Min Act: -0.0001

Data Index: 1312122 (C4 (Web Text))

Max Activating Token Index: 594

Text #16

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.5383. Min Act: -0.0001

Data Index: 541050 (C4 (Web Text))

Max Activating Token Index: 225

Text #17

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.5280. Min Act: -0.0001

Data Index: 691367 (C4 (Web Text))

Max Activating Token Index: 992

Text #18

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.5126. Min Act: -0.0001

Data Index: 1029042 (C4 (Web Text))

Max Activating Token Index: 117

Text #19

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.5772. Min Act: -0.0001

Data Index: 82039 (C4 (Web Text))

Max Activating Token Index: 911