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

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

Neuron 3332 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4878. Min Range: -4.4878

Max Act: 4.4878. Min Act: -0.0000

Data Index: 101401 (C4 (Web Text))

Max Activating Token Index: 147

Text #1

Max Range: 4.4878. Min Range: -4.4878

Max Act: 3.3040. Min Act: -0.0001

Data Index: 276630 (C4 (Web Text))

Max Activating Token Index: 615

Text #2

Max Range: 4.4878. Min Range: -4.4878

Max Act: 3.1274. Min Act: -0.0000

Data Index: 16523 (C4 (Web Text))

Max Activating Token Index: 967

Text #3

Max Range: 4.4878. Min Range: -4.4878

Max Act: 3.1811. Min Act: -0.0000

Data Index: 705250 (C4 (Web Text))

Max Activating Token Index: 565

Text #4

Max Range: 4.4878. Min Range: -4.4878

Max Act: 3.3874. Min Act: -0.0000

Data Index: 319882 (C4 (Web Text))

Max Activating Token Index: 197

Text #5

Max Range: 4.4878. Min Range: -4.4878

Max Act: 3.0371. Min Act: -0.0001

Data Index: 1379339 (Python Code)

Max Activating Token Index: 539

Text #6

Max Range: 4.4878. Min Range: -4.4878

Max Act: 2.7918. Min Act: -0.0000

Data Index: 445843 (C4 (Web Text))

Max Activating Token Index: 523

Text #7

Max Range: 4.4878. Min Range: -4.4878

Max Act: 2.9295. Min Act: -0.0001

Data Index: 1585786 (Python Code)

Max Activating Token Index: 622

Text #8

Max Range: 4.4878. Min Range: -4.4878

Max Act: 2.6391. Min Act: -0.0000

Data Index: 1011523 (C4 (Web Text))

Max Activating Token Index: 504

Text #9

Max Range: 4.4878. Min Range: -4.4878

Max Act: 2.6455. Min Act: -0.0000

Data Index: 347049 (C4 (Web Text))

Max Activating Token Index: 997

Text #10

Max Range: 4.4878. Min Range: -4.4878

Max Act: 2.7173. Min Act: -0.0001

Data Index: 329048 (C4 (Web Text))

Max Activating Token Index: 134

Text #11

Max Range: 4.4878. Min Range: -4.4878

Max Act: 2.5656. Min Act: -0.0000

Data Index: 816743 (C4 (Web Text))

Max Activating Token Index: 249

Text #12

Max Range: 4.4878. Min Range: -4.4878

Max Act: 2.4543. Min Act: -0.0001

Data Index: 1107774 (C4 (Web Text))

Max Activating Token Index: 696

Text #13

Max Range: 4.4878. Min Range: -4.4878

Max Act: 2.4594. Min Act: -0.0001

Data Index: 1635922 (Python Code)

Max Activating Token Index: 89

Text #14

Max Range: 4.4878. Min Range: -4.4878

Max Act: 2.5381. Min Act: -0.0001

Data Index: 1392360 (Python Code)

Max Activating Token Index: 743

Text #15

Max Range: 4.4878. Min Range: -4.4878

Max Act: 2.3263. Min Act: -0.0000

Data Index: 1612564 (Python Code)

Max Activating Token Index: 91

Text #16

Max Range: 4.4878. Min Range: -4.4878

Max Act: 2.4873. Min Act: -0.0001

Data Index: 1533181 (Python Code)

Max Activating Token Index: 583

Text #17

Max Range: 4.4878. Min Range: -4.4878

Max Act: 2.3465. Min Act: -0.0000

Data Index: 311858 (C4 (Web Text))

Max Activating Token Index: 823

Text #18

Max Range: 4.4878. Min Range: -4.4878

Max Act: 2.3201. Min Act: -0.0000

Data Index: 1186181 (C4 (Web Text))

Max Activating Token Index: 937

Text #19

Max Range: 4.4878. Min Range: -4.4878

Max Act: 2.3822. Min Act: -0.0000

Data Index: 1638703 (Python Code)

Max Activating Token Index: 707