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

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

Neuron 2391 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0891. Min Range: -1.0891

Max Act: 1.0891. Min Act: -0.0001

Data Index: 886318 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 1.0891. Min Range: -1.0891

Max Act: 0.9653. Min Act: -0.0001

Data Index: 396532 (C4 (Web Text))

Max Activating Token Index: 424

Text #2

Max Range: 1.0891. Min Range: -1.0891

Max Act: 0.8728. Min Act: -0.0001

Data Index: 636728 (C4 (Web Text))

Max Activating Token Index: 923

Text #3

Max Range: 1.0891. Min Range: -1.0891

Max Act: 0.8345. Min Act: -0.0001

Data Index: 1155245 (C4 (Web Text))

Max Activating Token Index: 21

Text #4

Max Range: 1.0891. Min Range: -1.0891

Max Act: 0.8379. Min Act: -0.0001

Data Index: 1156723 (C4 (Web Text))

Max Activating Token Index: 127

Text #5

Max Range: 1.0891. Min Range: -1.0891

Max Act: 0.7719. Min Act: -0.0001

Data Index: 575568 (C4 (Web Text))

Max Activating Token Index: 909

Text #6

Max Range: 1.0891. Min Range: -1.0891

Max Act: 0.7960. Min Act: -0.0001

Data Index: 1555328 (Python Code)

Max Activating Token Index: 939

Text #7

Max Range: 1.0891. Min Range: -1.0891

Max Act: 0.7540. Min Act: -0.0001

Data Index: 1248066 (C4 (Web Text))

Max Activating Token Index: 143

Text #8

Max Range: 1.0891. Min Range: -1.0891

Max Act: 0.7535. Min Act: -0.0001

Data Index: 406604 (C4 (Web Text))

Max Activating Token Index: 81

Text #9

Max Range: 1.0891. Min Range: -1.0891

Max Act: 0.7414. Min Act: -0.0001

Data Index: 311353 (C4 (Web Text))

Max Activating Token Index: 614

Text #10

Max Range: 1.0891. Min Range: -1.0891

Max Act: 0.7352. Min Act: -0.0001

Data Index: 803305 (C4 (Web Text))

Max Activating Token Index: 432

Text #11

Max Range: 1.0891. Min Range: -1.0891

Max Act: 0.7255. Min Act: -0.0001

Data Index: 645393 (C4 (Web Text))

Max Activating Token Index: 875

Text #12

Max Range: 1.0891. Min Range: -1.0891

Max Act: 0.7044. Min Act: -0.0001

Data Index: 137845 (C4 (Web Text))

Max Activating Token Index: 268

Text #13

Max Range: 1.0891. Min Range: -1.0891

Max Act: 0.7641. Min Act: -0.0001

Data Index: 616653 (C4 (Web Text))

Max Activating Token Index: 266

Text #14

Max Range: 1.0891. Min Range: -1.0891

Max Act: 0.7414. Min Act: -0.0001

Data Index: 826701 (C4 (Web Text))

Max Activating Token Index: 424

Text #15

Max Range: 1.0891. Min Range: -1.0891

Max Act: 0.7387. Min Act: -0.0001

Data Index: 380241 (C4 (Web Text))

Max Activating Token Index: 385

Text #16

Max Range: 1.0891. Min Range: -1.0891

Max Act: 0.7269. Min Act: -0.0001

Data Index: 1205297 (C4 (Web Text))

Max Activating Token Index: 112

Text #17

Max Range: 1.0891. Min Range: -1.0891

Max Act: 0.7309. Min Act: -0.0001

Data Index: 352837 (C4 (Web Text))

Max Activating Token Index: 810

Text #18

Max Range: 1.0891. Min Range: -1.0891

Max Act: 0.7323. Min Act: -0.0001

Data Index: 48882 (C4 (Web Text))

Max Activating Token Index: 691

Text #19

Max Range: 1.0891. Min Range: -1.0891

Max Act: 0.7501. Min Act: -0.0001

Data Index: 505027 (C4 (Web Text))

Max Activating Token Index: 80