Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1363 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0898. Min Act: -0.0003

Data Index: 1288680 (C4 (Web Text))

Max Activating Token Index: 119

Text #1

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0884. Min Act: -0.0003

Data Index: 11248 (C4 (Web Text))

Max Activating Token Index: 223

Text #2

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0860. Min Act: -0.0003

Data Index: 406872 (C4 (Web Text))

Max Activating Token Index: 157

Text #3

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0839. Min Act: -0.0003

Data Index: 406616 (C4 (Web Text))

Max Activating Token Index: 469

Text #4

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0831. Min Act: -0.0003

Data Index: 143477 (C4 (Web Text))

Max Activating Token Index: 152

Text #5

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0806. Min Act: -0.0004

Data Index: 1264944 (C4 (Web Text))

Max Activating Token Index: 599

Text #6

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0812. Min Act: -0.0003

Data Index: 565548 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0801. Min Act: -0.0003

Data Index: 544671 (C4 (Web Text))

Max Activating Token Index: 327

Text #8

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0772. Min Act: -0.0003

Data Index: 196664 (C4 (Web Text))

Max Activating Token Index: 175

Text #9

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0768. Min Act: -0.0003

Data Index: 282397 (C4 (Web Text))

Max Activating Token Index: 360

Text #10

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0778. Min Act: -0.0003

Data Index: 416162 (C4 (Web Text))

Max Activating Token Index: 93

Text #11

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0751. Min Act: -0.0003

Data Index: 1503949 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0742. Min Act: -0.0003

Data Index: 111850 (C4 (Web Text))

Max Activating Token Index: 74

Text #13

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0738. Min Act: -0.0003

Data Index: 1105007 (C4 (Web Text))

Max Activating Token Index: 34

Text #14

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0723. Min Act: -0.0003

Data Index: 1648935 (Python Code)

Max Activating Token Index: 83

Text #15

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0707. Min Act: -0.0003

Data Index: 902090 (C4 (Web Text))

Max Activating Token Index: 140

Text #16

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0718. Min Act: -0.0003

Data Index: 1554576 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0739. Min Act: -0.0003

Data Index: 1086497 (C4 (Web Text))

Max Activating Token Index: 241

Text #18

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0705. Min Act: -0.0003

Data Index: 503763 (C4 (Web Text))

Max Activating Token Index: 562

Text #19

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0708. Min Act: -0.0003

Data Index: 1124591 (C4 (Web Text))

Max Activating Token Index: 23