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

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

Neuron 4699 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.5445. Min Range: -6.5445

Max Act: 6.5445. Min Act: -0.0000

Data Index: 1374385 (Python Code)

Max Activating Token Index: 119

Text #1

Max Range: 6.5445. Min Range: -6.5445

Max Act: 6.3834. Min Act: -0.0000

Data Index: 1543376 (Python Code)

Max Activating Token Index: 788

Text #2

Max Range: 6.5445. Min Range: -6.5445

Max Act: 6.0986. Min Act: -0.0000

Data Index: 1620549 (Python Code)

Max Activating Token Index: 773

Text #3

Max Range: 6.5445. Min Range: -6.5445

Max Act: 5.9180. Min Act: -0.0000

Data Index: 1544043 (Python Code)

Max Activating Token Index: 442

Text #4

Max Range: 6.5445. Min Range: -6.5445

Max Act: 5.8252. Min Act: -0.0000

Data Index: 1482186 (Python Code)

Max Activating Token Index: 674

Text #5

Max Range: 6.5445. Min Range: -6.5445

Max Act: 5.4791. Min Act: -0.0000

Data Index: 1405325 (Python Code)

Max Activating Token Index: 129

Text #6

Max Range: 6.5445. Min Range: -6.5445

Max Act: 5.8524. Min Act: -0.0000

Data Index: 1454241 (Python Code)

Max Activating Token Index: 275

Text #7

Max Range: 6.5445. Min Range: -6.5445

Max Act: 5.5044. Min Act: -0.0000

Data Index: 1414064 (Python Code)

Max Activating Token Index: 263

Text #8

Max Range: 6.5445. Min Range: -6.5445

Max Act: 5.6124. Min Act: -0.0000

Data Index: 1630533 (Python Code)

Max Activating Token Index: 994

Text #9

Max Range: 6.5445. Min Range: -6.5445

Max Act: 5.5524. Min Act: -0.0000

Data Index: 1453305 (Python Code)

Max Activating Token Index: 52

Text #10

Max Range: 6.5445. Min Range: -6.5445

Max Act: 5.4937. Min Act: -0.0000

Data Index: 1563187 (Python Code)

Max Activating Token Index: 810

Text #11

Max Range: 6.5445. Min Range: -6.5445

Max Act: 5.9652. Min Act: -0.0000

Data Index: 1422427 (Python Code)

Max Activating Token Index: 742

Text #12

Max Range: 6.5445. Min Range: -6.5445

Max Act: 5.2002. Min Act: -0.0000

Data Index: 1565720 (Python Code)

Max Activating Token Index: 338

Text #13

Max Range: 6.5445. Min Range: -6.5445

Max Act: 5.3287. Min Act: -0.0000

Data Index: 1406779 (Python Code)

Max Activating Token Index: 27

Text #14

Max Range: 6.5445. Min Range: -6.5445

Max Act: 5.1137. Min Act: -0.0000

Data Index: 1575234 (Python Code)

Max Activating Token Index: 595

Text #15

Max Range: 6.5445. Min Range: -6.5445

Max Act: 5.2581. Min Act: -0.0000

Data Index: 1415222 (Python Code)

Max Activating Token Index: 929

Text #16

Max Range: 6.5445. Min Range: -6.5445

Max Act: 5.4040. Min Act: -0.0000

Data Index: 1623655 (Python Code)

Max Activating Token Index: 303

Text #17

Max Range: 6.5445. Min Range: -6.5445

Max Act: 5.0693. Min Act: -0.0000

Data Index: 1386589 (Python Code)

Max Activating Token Index: 801

Text #18

Max Range: 6.5445. Min Range: -6.5445

Max Act: 4.8857. Min Act: -0.0000

Data Index: 1509829 (Python Code)

Max Activating Token Index: 785

Text #19

Max Range: 6.5445. Min Range: -6.5445

Max Act: 5.6306. Min Act: -0.0000

Data Index: 1575267 (Python Code)

Max Activating Token Index: 603