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

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

Neuron 1175 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.7582. Min Range: -1.7582

Max Act: 1.7582. Min Act: -0.0001

Data Index: 735222 (C4 (Web Text))

Max Activating Token Index: 306

Text #1

Max Range: 1.7582. Min Range: -1.7582

Max Act: 1.1998. Min Act: -0.0001

Data Index: 894702 (C4 (Web Text))

Max Activating Token Index: 768

Text #2

Max Range: 1.7582. Min Range: -1.7582

Max Act: 1.1050. Min Act: -0.0001

Data Index: 428543 (C4 (Web Text))

Max Activating Token Index: 253

Text #3

Max Range: 1.7582. Min Range: -1.7582

Max Act: 0.9898. Min Act: -0.0001

Data Index: 597174 (C4 (Web Text))

Max Activating Token Index: 665

Text #4

Max Range: 1.7582. Min Range: -1.7582

Max Act: 0.9355. Min Act: -0.0001

Data Index: 1118344 (C4 (Web Text))

Max Activating Token Index: 741

Text #5

Max Range: 1.7582. Min Range: -1.7582

Max Act: 1.1060. Min Act: -0.0001

Data Index: 977 (C4 (Web Text))

Max Activating Token Index: 840

Text #6

Max Range: 1.7582. Min Range: -1.7582

Max Act: 1.0725. Min Act: -0.0001

Data Index: 24685 (C4 (Web Text))

Max Activating Token Index: 965

Text #7

Max Range: 1.7582. Min Range: -1.7582

Max Act: 1.0575. Min Act: -0.0001

Data Index: 1185816 (C4 (Web Text))

Max Activating Token Index: 513

Text #8

Max Range: 1.7582. Min Range: -1.7582

Max Act: 0.9658. Min Act: -0.0001

Data Index: 496720 (C4 (Web Text))

Max Activating Token Index: 675

Text #9

Max Range: 1.7582. Min Range: -1.7582

Max Act: 0.9485. Min Act: -0.0001

Data Index: 1101968 (C4 (Web Text))

Max Activating Token Index: 631

Text #10

Max Range: 1.7582. Min Range: -1.7582

Max Act: 0.9947. Min Act: -0.0001

Data Index: 337852 (C4 (Web Text))

Max Activating Token Index: 106

Text #11

Max Range: 1.7582. Min Range: -1.7582

Max Act: 0.9881. Min Act: -0.0001

Data Index: 955337 (C4 (Web Text))

Max Activating Token Index: 544

Text #12

Max Range: 1.7582. Min Range: -1.7582

Max Act: 0.8727. Min Act: -0.0001

Data Index: 16395 (C4 (Web Text))

Max Activating Token Index: 350

Text #13

Max Range: 1.7582. Min Range: -1.7582

Max Act: 0.9838. Min Act: -0.0001

Data Index: 285145 (C4 (Web Text))

Max Activating Token Index: 636

Text #14

Max Range: 1.7582. Min Range: -1.7582

Max Act: 0.9176. Min Act: -0.0001

Data Index: 679372 (C4 (Web Text))

Max Activating Token Index: 245

Text #15

Max Range: 1.7582. Min Range: -1.7582

Max Act: 0.9827. Min Act: -0.0001

Data Index: 745851 (C4 (Web Text))

Max Activating Token Index: 822

Text #16

Max Range: 1.7582. Min Range: -1.7582

Max Act: 0.8947. Min Act: -0.0001

Data Index: 275867 (C4 (Web Text))

Max Activating Token Index: 366

Text #17

Max Range: 1.7582. Min Range: -1.7582

Max Act: 0.8634. Min Act: -0.0001

Data Index: 240593 (C4 (Web Text))

Max Activating Token Index: 741

Text #18

Max Range: 1.7582. Min Range: -1.7582

Max Act: 0.9191. Min Act: -0.0001

Data Index: 795021 (C4 (Web Text))

Max Activating Token Index: 71

Text #19

Max Range: 1.7582. Min Range: -1.7582

Max Act: 0.8799. Min Act: -0.0001

Data Index: 149507 (C4 (Web Text))

Max Activating Token Index: 779