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

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

Neuron 4687 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: 0.3820. Min Range: -0.3820

Max Act: 0.3820. Min Act: -0.0000

Data Index: 429947 (C4 (Web Text))

Max Activating Token Index: 350

Text #1

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3627. Min Act: -0.0000

Data Index: 789143 (C4 (Web Text))

Max Activating Token Index: 191

Text #2

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3350. Min Act: -0.0000

Data Index: 934752 (C4 (Web Text))

Max Activating Token Index: 860

Text #3

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3413. Min Act: -0.0000

Data Index: 693543 (C4 (Web Text))

Max Activating Token Index: 219

Text #4

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3066. Min Act: -0.0000

Data Index: 628498 (C4 (Web Text))

Max Activating Token Index: 291

Text #5

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3317. Min Act: -0.0000

Data Index: 357146 (C4 (Web Text))

Max Activating Token Index: 375

Text #6

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3453. Min Act: -0.0000

Data Index: 506525 (C4 (Web Text))

Max Activating Token Index: 314

Text #7

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3188. Min Act: -0.0000

Data Index: 1054068 (C4 (Web Text))

Max Activating Token Index: 886

Text #8

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3286. Min Act: -0.0000

Data Index: 711295 (C4 (Web Text))

Max Activating Token Index: 521

Text #9

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3255. Min Act: -0.0000

Data Index: 223307 (C4 (Web Text))

Max Activating Token Index: 937

Text #10

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3481. Min Act: -0.0000

Data Index: 510939 (C4 (Web Text))

Max Activating Token Index: 583

Text #11

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3188. Min Act: -0.0000

Data Index: 814557 (C4 (Web Text))

Max Activating Token Index: 675

Text #12

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3299. Min Act: -0.0000

Data Index: 23376 (C4 (Web Text))

Max Activating Token Index: 703

Text #13

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3502. Min Act: -0.0000

Data Index: 25256 (C4 (Web Text))

Max Activating Token Index: 985

Text #14

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2950. Min Act: -0.0000

Data Index: 643152 (C4 (Web Text))

Max Activating Token Index: 415

Text #15

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3304. Min Act: -0.0000

Data Index: 667973 (C4 (Web Text))

Max Activating Token Index: 532

Text #16

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3003. Min Act: -0.0000

Data Index: 161802 (C4 (Web Text))

Max Activating Token Index: 804

Text #17

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2979. Min Act: -0.0000

Data Index: 213095 (C4 (Web Text))

Max Activating Token Index: 864

Text #18

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3066. Min Act: -0.0000

Data Index: 126873 (C4 (Web Text))

Max Activating Token Index: 78

Text #19

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2899. Min Act: -0.0000

Data Index: 16056 (C4 (Web Text))

Max Activating Token Index: 666