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

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

Neuron 4813 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.6084. Min Act: -0.0000

Data Index: 976708 (C4 (Web Text))

Max Activating Token Index: 784

Text #1

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.5131. Min Act: -0.0000

Data Index: 895835 (C4 (Web Text))

Max Activating Token Index: 915

Text #2

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.5120. Min Act: -0.0000

Data Index: 1281918 (C4 (Web Text))

Max Activating Token Index: 636

Text #3

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.5044. Min Act: -0.0000

Data Index: 694966 (C4 (Web Text))

Max Activating Token Index: 904

Text #4

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.4830. Min Act: -0.0000

Data Index: 40798 (C4 (Web Text))

Max Activating Token Index: 805

Text #5

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.4638. Min Act: -0.0000

Data Index: 1017706 (C4 (Web Text))

Max Activating Token Index: 570

Text #6

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.4784. Min Act: -0.0000

Data Index: 966926 (C4 (Web Text))

Max Activating Token Index: 895

Text #7

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.4459. Min Act: -0.0000

Data Index: 1001912 (C4 (Web Text))

Max Activating Token Index: 550

Text #8

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.4448. Min Act: -0.0000

Data Index: 731215 (C4 (Web Text))

Max Activating Token Index: 664

Text #9

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.4612. Min Act: -0.0000

Data Index: 1245356 (C4 (Web Text))

Max Activating Token Index: 984

Text #10

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.4570. Min Act: -0.0000

Data Index: 1248676 (C4 (Web Text))

Max Activating Token Index: 623

Text #11

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.4578. Min Act: -0.0000

Data Index: 496617 (C4 (Web Text))

Max Activating Token Index: 333

Text #12

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.4403. Min Act: -0.0000

Data Index: 426462 (C4 (Web Text))

Max Activating Token Index: 574

Text #13

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.4688. Min Act: -0.0000

Data Index: 1288253 (C4 (Web Text))

Max Activating Token Index: 192

Text #14

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.4677. Min Act: -0.0000

Data Index: 950997 (C4 (Web Text))

Max Activating Token Index: 573

Text #15

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.4319. Min Act: -0.0000

Data Index: 800671 (C4 (Web Text))

Max Activating Token Index: 424

Text #16

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.4463. Min Act: -0.0000

Data Index: 939576 (C4 (Web Text))

Max Activating Token Index: 661

Text #17

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.4297. Min Act: -0.0000

Data Index: 909843 (C4 (Web Text))

Max Activating Token Index: 647

Text #18

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.4388. Min Act: -0.0000

Data Index: 1031441 (C4 (Web Text))

Max Activating Token Index: 497

Text #19

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.4529. Min Act: -0.0000

Data Index: 1247874 (C4 (Web Text))

Max Activating Token Index: 864