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

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

Neuron 159 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8609. Min Range: -0.8609

Max Act: 0.8510. Min Act: -0.0000

Data Index: 597791 (C4 (Web Text))

Max Activating Token Index: 940

Text #1

Max Range: 0.8609. Min Range: -0.8609

Max Act: 0.8007. Min Act: -0.0000

Data Index: 20734 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 0.8609. Min Range: -0.8609

Max Act: 0.8609. Min Act: -0.0000

Data Index: 919283 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.8609. Min Range: -0.8609

Max Act: 0.7967. Min Act: -0.0000

Data Index: 699893 (C4 (Web Text))

Max Activating Token Index: 999

Text #4

Max Range: 0.8609. Min Range: -0.8609

Max Act: 0.8459. Min Act: -0.0000

Data Index: 362293 (C4 (Web Text))

Max Activating Token Index: 912

Text #5

Max Range: 0.8609. Min Range: -0.8609

Max Act: 0.8235. Min Act: -0.0000

Data Index: 237308 (C4 (Web Text))

Max Activating Token Index: 871

Text #6

Max Range: 0.8609. Min Range: -0.8609

Max Act: 0.7872. Min Act: -0.0000

Data Index: 3413 (C4 (Web Text))

Max Activating Token Index: 129

Text #7

Max Range: 0.8609. Min Range: -0.8609

Max Act: 0.7612. Min Act: -0.0000

Data Index: 643964 (C4 (Web Text))

Max Activating Token Index: 515

Text #8

Max Range: 0.8609. Min Range: -0.8609

Max Act: 0.7846. Min Act: -0.0000

Data Index: 671973 (C4 (Web Text))

Max Activating Token Index: 199

Text #9

Max Range: 0.8609. Min Range: -0.8609

Max Act: 0.7172. Min Act: -0.0000

Data Index: 741842 (C4 (Web Text))

Max Activating Token Index: 739

Text #10

Max Range: 0.8609. Min Range: -0.8609

Max Act: 0.7621. Min Act: -0.0000

Data Index: 824087 (C4 (Web Text))

Max Activating Token Index: 293

Text #11

Max Range: 0.8609. Min Range: -0.8609

Max Act: 0.7059. Min Act: -0.0000

Data Index: 1143925 (C4 (Web Text))

Max Activating Token Index: 392

Text #12

Max Range: 0.8609. Min Range: -0.8609

Max Act: 0.6789. Min Act: -0.0000

Data Index: 755048 (C4 (Web Text))

Max Activating Token Index: 326

Text #13

Max Range: 0.8609. Min Range: -0.8609

Max Act: 0.6954. Min Act: -0.0000

Data Index: 932766 (C4 (Web Text))

Max Activating Token Index: 1000

Text #14

Max Range: 0.8609. Min Range: -0.8609

Max Act: 0.7006. Min Act: -0.0000

Data Index: 824596 (C4 (Web Text))

Max Activating Token Index: 125

Text #15

Max Range: 0.8609. Min Range: -0.8609

Max Act: 0.6750. Min Act: -0.0000

Data Index: 774982 (C4 (Web Text))

Max Activating Token Index: 205

Text #16

Max Range: 0.8609. Min Range: -0.8609

Max Act: 0.6716. Min Act: -0.0000

Data Index: 617606 (C4 (Web Text))

Max Activating Token Index: 597

Text #17

Max Range: 0.8609. Min Range: -0.8609

Max Act: 0.6925. Min Act: -0.0000

Data Index: 63797 (C4 (Web Text))

Max Activating Token Index: 736

Text #18

Max Range: 0.8609. Min Range: -0.8609

Max Act: 0.6897. Min Act: -0.0000

Data Index: 587120 (C4 (Web Text))

Max Activating Token Index: 741

Text #19

Max Range: 0.8609. Min Range: -0.8609

Max Act: 0.6891. Min Act: -0.0000

Data Index: 461009 (C4 (Web Text))

Max Activating Token Index: 265