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

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

Neuron 1941 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9736. Min Range: -2.9736

Max Act: 2.9736. Min Act: 0.0000

Data Index: 1323190 (C4 (Web Text))

Max Activating Token Index: 887

Text #1

Max Range: 2.9736. Min Range: -2.9736

Max Act: 2.2632. Min Act: -0.0000

Data Index: 1227814 (C4 (Web Text))

Max Activating Token Index: 408

Text #2

Max Range: 2.9736. Min Range: -2.9736

Max Act: 2.0803. Min Act: -0.0000

Data Index: 539467 (C4 (Web Text))

Max Activating Token Index: 382

Text #3

Max Range: 2.9736. Min Range: -2.9736

Max Act: 2.1553. Min Act: -0.0000

Data Index: 800705 (C4 (Web Text))

Max Activating Token Index: 181

Text #4

Max Range: 2.9736. Min Range: -2.9736

Max Act: 1.8135. Min Act: -0.0000

Data Index: 1648574 (Python Code)

Max Activating Token Index: 388

Text #5

Max Range: 2.9736. Min Range: -2.9736

Max Act: 1.7033. Min Act: -0.0000

Data Index: 160719 (C4 (Web Text))

Max Activating Token Index: 477

Text #6

Max Range: 2.9736. Min Range: -2.9736

Max Act: 1.5938. Min Act: -0.0000

Data Index: 521219 (C4 (Web Text))

Max Activating Token Index: 575

Text #7

Max Range: 2.9736. Min Range: -2.9736

Max Act: 1.6837. Min Act: -0.0000

Data Index: 1388859 (Python Code)

Max Activating Token Index: 510

Text #8

Max Range: 2.9736. Min Range: -2.9736

Max Act: 1.6168. Min Act: -0.0000

Data Index: 729081 (C4 (Web Text))

Max Activating Token Index: 983

Text #9

Max Range: 2.9736. Min Range: -2.9736

Max Act: 1.6046. Min Act: -0.0000

Data Index: 1618826 (Python Code)

Max Activating Token Index: 579

Text #10

Max Range: 2.9736. Min Range: -2.9736

Max Act: 1.7609. Min Act: -0.0000

Data Index: 1361355 (Python Code)

Max Activating Token Index: 728

Text #11

Max Range: 2.9736. Min Range: -2.9736

Max Act: 1.3979. Min Act: -0.0000

Data Index: 818688 (C4 (Web Text))

Max Activating Token Index: 696

Text #12

Max Range: 2.9736. Min Range: -2.9736

Max Act: 1.5265. Min Act: -0.0000

Data Index: 1441908 (Python Code)

Max Activating Token Index: 292

Text #13

Max Range: 2.9736. Min Range: -2.9736

Max Act: 1.6376. Min Act: -0.0000

Data Index: 1492709 (Python Code)

Max Activating Token Index: 273

Text #14

Max Range: 2.9736. Min Range: -2.9736

Max Act: 1.5322. Min Act: -0.0000

Data Index: 1273211 (C4 (Web Text))

Max Activating Token Index: 717

Text #15

Max Range: 2.9736. Min Range: -2.9736

Max Act: 1.4027. Min Act: -0.0000

Data Index: 1380614 (Python Code)

Max Activating Token Index: 836

Text #16

Max Range: 2.9736. Min Range: -2.9736

Max Act: 1.2969. Min Act: 0.0000

Data Index: 860006 (C4 (Web Text))

Max Activating Token Index: 250

Text #17

Max Range: 2.9736. Min Range: -2.9736

Max Act: 1.5677. Min Act: -0.0000

Data Index: 1360485 (Python Code)

Max Activating Token Index: 868

Text #18

Max Range: 2.9736. Min Range: -2.9736

Max Act: 1.3875. Min Act: -0.0000

Data Index: 102869 (C4 (Web Text))

Max Activating Token Index: 467

Text #19

Max Range: 2.9736. Min Range: -2.9736

Max Act: 1.4622. Min Act: -0.0000

Data Index: 1543150 (Python Code)

Max Activating Token Index: 343