Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4769 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1066. Min Range: -1.1066

Max Act: 0.9967. Min Act: -0.0000

Data Index: 1355264 (C4 (Web Text))

Max Activating Token Index: 445

Text #1

Max Range: 1.1066. Min Range: -1.1066

Max Act: 1.1066. Min Act: -0.0000

Data Index: 514174 (C4 (Web Text))

Max Activating Token Index: 106

Text #2

Max Range: 1.1066. Min Range: -1.1066

Max Act: 0.9518. Min Act: -0.0000

Data Index: 288373 (C4 (Web Text))

Max Activating Token Index: 292

Text #3

Max Range: 1.1066. Min Range: -1.1066

Max Act: 0.8808. Min Act: -0.0000

Data Index: 228162 (C4 (Web Text))

Max Activating Token Index: 324

Text #4

Max Range: 1.1066. Min Range: -1.1066

Max Act: 0.9009. Min Act: -0.0000

Data Index: 663007 (C4 (Web Text))

Max Activating Token Index: 494

Text #5

Max Range: 1.1066. Min Range: -1.1066

Max Act: 0.8886. Min Act: -0.0000

Data Index: 1002064 (C4 (Web Text))

Max Activating Token Index: 199

Text #6

Max Range: 1.1066. Min Range: -1.1066

Max Act: 0.7744. Min Act: -0.0000

Data Index: 1193662 (C4 (Web Text))

Max Activating Token Index: 740

Text #7

Max Range: 1.1066. Min Range: -1.1066

Max Act: 0.8705. Min Act: -0.0000

Data Index: 1116657 (C4 (Web Text))

Max Activating Token Index: 467

Text #8

Max Range: 1.1066. Min Range: -1.1066

Max Act: 0.8940. Min Act: -0.0000

Data Index: 508471 (C4 (Web Text))

Max Activating Token Index: 809

Text #9

Max Range: 1.1066. Min Range: -1.1066

Max Act: 0.8928. Min Act: -0.0000

Data Index: 791795 (C4 (Web Text))

Max Activating Token Index: 704

Text #10

Max Range: 1.1066. Min Range: -1.1066

Max Act: 0.8302. Min Act: -0.0000

Data Index: 693874 (C4 (Web Text))

Max Activating Token Index: 520

Text #11

Max Range: 1.1066. Min Range: -1.1066

Max Act: 0.8207. Min Act: -0.0000

Data Index: 761731 (C4 (Web Text))

Max Activating Token Index: 911

Text #12

Max Range: 1.1066. Min Range: -1.1066

Max Act: 0.7486. Min Act: -0.0000

Data Index: 889792 (C4 (Web Text))

Max Activating Token Index: 477

Text #13

Max Range: 1.1066. Min Range: -1.1066

Max Act: 0.7901. Min Act: -0.0000

Data Index: 543492 (C4 (Web Text))

Max Activating Token Index: 622

Text #14

Max Range: 1.1066. Min Range: -1.1066

Max Act: 0.7399. Min Act: -0.0000

Data Index: 1392765 (Python Code)

Max Activating Token Index: 237

Text #15

Max Range: 1.1066. Min Range: -1.1066

Max Act: 0.6834. Min Act: -0.0000

Data Index: 1237040 (C4 (Web Text))

Max Activating Token Index: 107

Text #16

Max Range: 1.1066. Min Range: -1.1066

Max Act: 0.7717. Min Act: -0.0000

Data Index: 383370 (C4 (Web Text))

Max Activating Token Index: 244

Text #17

Max Range: 1.1066. Min Range: -1.1066

Max Act: 0.7250. Min Act: -0.0000

Data Index: 953384 (C4 (Web Text))

Max Activating Token Index: 134

Text #18

Max Range: 1.1066. Min Range: -1.1066

Max Act: 0.7245. Min Act: -0.0000

Data Index: 1135586 (C4 (Web Text))

Max Activating Token Index: 400

Text #19

Max Range: 1.1066. Min Range: -1.1066

Max Act: 0.7168. Min Act: -0.0000

Data Index: 1593158 (Python Code)

Max Activating Token Index: 379