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

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

Neuron 389 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.5875. Min Act: -0.0001

Data Index: 90210 (C4 (Web Text))

Max Activating Token Index: 907

Text #1

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.5504. Min Act: -0.0001

Data Index: 130610 (C4 (Web Text))

Max Activating Token Index: 805

Text #2

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.5247. Min Act: -0.0000

Data Index: 726079 (C4 (Web Text))

Max Activating Token Index: 302

Text #3

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4613. Min Act: -0.0001

Data Index: 546840 (C4 (Web Text))

Max Activating Token Index: 248

Text #4

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4785. Min Act: -0.0001

Data Index: 280860 (C4 (Web Text))

Max Activating Token Index: 559

Text #5

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4880. Min Act: -0.0000

Data Index: 906596 (C4 (Web Text))

Max Activating Token Index: 777

Text #6

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4573. Min Act: -0.0001

Data Index: 68689 (C4 (Web Text))

Max Activating Token Index: 1004

Text #7

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4717. Min Act: -0.0000

Data Index: 201396 (C4 (Web Text))

Max Activating Token Index: 123

Text #8

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4538. Min Act: -0.0001

Data Index: 977319 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4611. Min Act: -0.0001

Data Index: 219959 (C4 (Web Text))

Max Activating Token Index: 273

Text #10

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4318. Min Act: -0.0000

Data Index: 295220 (C4 (Web Text))

Max Activating Token Index: 344

Text #11

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4530. Min Act: -0.0000

Data Index: 1215501 (C4 (Web Text))

Max Activating Token Index: 615

Text #12

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4080. Min Act: -0.0000

Data Index: 583591 (C4 (Web Text))

Max Activating Token Index: 122

Text #13

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4078. Min Act: -0.0001

Data Index: 303330 (C4 (Web Text))

Max Activating Token Index: 855

Text #14

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4221. Min Act: -0.0000

Data Index: 593876 (C4 (Web Text))

Max Activating Token Index: 511

Text #15

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4058. Min Act: -0.0001

Data Index: 1021697 (C4 (Web Text))

Max Activating Token Index: 886

Text #16

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4194. Min Act: -0.0000

Data Index: 770165 (C4 (Web Text))

Max Activating Token Index: 874

Text #17

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4069. Min Act: -0.0000

Data Index: 569315 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4152. Min Act: -0.0000

Data Index: 389754 (C4 (Web Text))

Max Activating Token Index: 914

Text #19

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4147. Min Act: -0.0000

Data Index: 410279 (C4 (Web Text))

Max Activating Token Index: 480