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

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

Neuron 3891 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: 0.8125. Min Range: -0.8125

Max Act: 0.8125. Min Act: -0.0000

Data Index: 226080 (C4 (Web Text))

Max Activating Token Index: 874

Text #1

Max Range: 0.8125. Min Range: -0.8125

Max Act: 0.8026. Min Act: -0.0001

Data Index: 748201 (C4 (Web Text))

Max Activating Token Index: 1008

Text #2

Max Range: 0.8125. Min Range: -0.8125

Max Act: 0.6877. Min Act: -0.0001

Data Index: 346982 (C4 (Web Text))

Max Activating Token Index: 607

Text #3

Max Range: 0.8125. Min Range: -0.8125

Max Act: 0.6631. Min Act: -0.0000

Data Index: 760012 (C4 (Web Text))

Max Activating Token Index: 841

Text #4

Max Range: 0.8125. Min Range: -0.8125

Max Act: 0.6768. Min Act: -0.0000

Data Index: 800154 (C4 (Web Text))

Max Activating Token Index: 110

Text #5

Max Range: 0.8125. Min Range: -0.8125

Max Act: 0.6404. Min Act: -0.0000

Data Index: 179249 (C4 (Web Text))

Max Activating Token Index: 858

Text #6

Max Range: 0.8125. Min Range: -0.8125

Max Act: 0.6181. Min Act: -0.0001

Data Index: 661003 (C4 (Web Text))

Max Activating Token Index: 538

Text #7

Max Range: 0.8125. Min Range: -0.8125

Max Act: 0.5965. Min Act: -0.0000

Data Index: 949316 (C4 (Web Text))

Max Activating Token Index: 992

Text #8

Max Range: 0.8125. Min Range: -0.8125

Max Act: 0.6295. Min Act: -0.0001

Data Index: 464553 (C4 (Web Text))

Max Activating Token Index: 325

Text #9

Max Range: 0.8125. Min Range: -0.8125

Max Act: 0.6300. Min Act: -0.0000

Data Index: 1092816 (C4 (Web Text))

Max Activating Token Index: 914

Text #10

Max Range: 0.8125. Min Range: -0.8125

Max Act: 0.6181. Min Act: -0.0000

Data Index: 341104 (C4 (Web Text))

Max Activating Token Index: 394

Text #11

Max Range: 0.8125. Min Range: -0.8125

Max Act: 0.5949. Min Act: -0.0001

Data Index: 94766 (C4 (Web Text))

Max Activating Token Index: 533

Text #12

Max Range: 0.8125. Min Range: -0.8125

Max Act: 0.6049. Min Act: -0.0000

Data Index: 24675 (C4 (Web Text))

Max Activating Token Index: 863

Text #13

Max Range: 0.8125. Min Range: -0.8125

Max Act: 0.5996. Min Act: -0.0000

Data Index: 794414 (C4 (Web Text))

Max Activating Token Index: 474

Text #14

Max Range: 0.8125. Min Range: -0.8125

Max Act: 0.5807. Min Act: -0.0001

Data Index: 1267081 (C4 (Web Text))

Max Activating Token Index: 598

Text #15

Max Range: 0.8125. Min Range: -0.8125

Max Act: 0.5449. Min Act: -0.0000

Data Index: 1241404 (C4 (Web Text))

Max Activating Token Index: 950

Text #16

Max Range: 0.8125. Min Range: -0.8125

Max Act: 0.5556. Min Act: -0.0000

Data Index: 249466 (C4 (Web Text))

Max Activating Token Index: 519

Text #17

Max Range: 0.8125. Min Range: -0.8125

Max Act: 0.5068. Min Act: -0.0000

Data Index: 1281791 (C4 (Web Text))

Max Activating Token Index: 908

Text #18

Max Range: 0.8125. Min Range: -0.8125

Max Act: 0.5432. Min Act: -0.0001

Data Index: 408541 (C4 (Web Text))

Max Activating Token Index: 355

Text #19

Max Range: 0.8125. Min Range: -0.8125

Max Act: 0.5703. Min Act: -0.0001

Data Index: 980270 (C4 (Web Text))

Max Activating Token Index: 666