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

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

Neuron 736 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.7767. Min Act: 0.0001

Data Index: 330298 (C4 (Web Text))

Max Activating Token Index: 134

Text #1

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.7503. Min Act: -0.0000

Data Index: 1090227 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.7294. Min Act: -0.0000

Data Index: 1045408 (C4 (Web Text))

Max Activating Token Index: 237

Text #3

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.6885. Min Act: -0.0000

Data Index: 1282893 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.6426. Min Act: -0.0000

Data Index: 619211 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.6338. Min Act: 0.0003

Data Index: 986816 (C4 (Web Text))

Max Activating Token Index: 250

Text #6

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.6262. Min Act: 0.0001

Data Index: 217920 (C4 (Web Text))

Max Activating Token Index: 392

Text #7

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.6000. Min Act: 0.0000

Data Index: 272716 (C4 (Web Text))

Max Activating Token Index: 63

Text #8

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.5978. Min Act: -0.0000

Data Index: 609218 (C4 (Web Text))

Max Activating Token Index: 336

Text #9

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.4928. Min Act: -0.0001

Data Index: 1124407 (C4 (Web Text))

Max Activating Token Index: 246

Text #10

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.5320. Min Act: -0.0001

Data Index: 470451 (C4 (Web Text))

Max Activating Token Index: 191

Text #11

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.5290. Min Act: 0.0001

Data Index: 12073 (C4 (Web Text))

Max Activating Token Index: 437

Text #12

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.5602. Min Act: -0.0000

Data Index: 1009547 (C4 (Web Text))

Max Activating Token Index: 422

Text #13

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.5247. Min Act: -0.0000

Data Index: 750911 (C4 (Web Text))

Max Activating Token Index: 650

Text #14

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.5198. Min Act: -0.0001

Data Index: 601750 (C4 (Web Text))

Max Activating Token Index: 275

Text #15

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.5103. Min Act: -0.0000

Data Index: 43892 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.4932. Min Act: -0.0000

Data Index: 688393 (C4 (Web Text))

Max Activating Token Index: 303

Text #17

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.5174. Min Act: -0.0001

Data Index: 401128 (C4 (Web Text))

Max Activating Token Index: 430

Text #18

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.5812. Min Act: -0.0000

Data Index: 1125884 (C4 (Web Text))

Max Activating Token Index: 885

Text #19

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.5374. Min Act: -0.0000

Data Index: 1267505 (C4 (Web Text))

Max Activating Token Index: 634