Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2733 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0728. Min Act: -0.0004

Data Index: 43140 (C4 (Web Text))

Max Activating Token Index: 927

Text #1

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0700. Min Act: -0.0004

Data Index: 1222905 (C4 (Web Text))

Max Activating Token Index: 281

Text #2

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0664. Min Act: -0.0004

Data Index: 1238696 (C4 (Web Text))

Max Activating Token Index: 52

Text #3

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0678. Min Act: -0.0004

Data Index: 99320 (C4 (Web Text))

Max Activating Token Index: 317

Text #4

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0649. Min Act: -0.0004

Data Index: 896219 (C4 (Web Text))

Max Activating Token Index: 589

Text #5

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0645. Min Act: -0.0004

Data Index: 944161 (C4 (Web Text))

Max Activating Token Index: 843

Text #6

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0663. Min Act: -0.0004

Data Index: 822446 (C4 (Web Text))

Max Activating Token Index: 815

Text #7

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0662. Min Act: -0.0004

Data Index: 71566 (C4 (Web Text))

Max Activating Token Index: 264

Text #8

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0594. Min Act: -0.0004

Data Index: 1190009 (C4 (Web Text))

Max Activating Token Index: 40

Text #9

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0554. Min Act: -0.0004

Data Index: 484204 (C4 (Web Text))

Max Activating Token Index: 300

Text #10

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0633. Min Act: -0.0004

Data Index: 680183 (C4 (Web Text))

Max Activating Token Index: 119

Text #11

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0625. Min Act: -0.0004

Data Index: 267767 (C4 (Web Text))

Max Activating Token Index: 930

Text #12

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0652. Min Act: -0.0004

Data Index: 1188073 (C4 (Web Text))

Max Activating Token Index: 14

Text #13

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0598. Min Act: -0.0004

Data Index: 447025 (C4 (Web Text))

Max Activating Token Index: 816

Text #14

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0596. Min Act: -0.0004

Data Index: 1089295 (C4 (Web Text))

Max Activating Token Index: 686

Text #15

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0615. Min Act: -0.0004

Data Index: 674450 (C4 (Web Text))

Max Activating Token Index: 130

Text #16

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0639. Min Act: -0.0004

Data Index: 86038 (C4 (Web Text))

Max Activating Token Index: 243

Text #17

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0639. Min Act: -0.0004

Data Index: 581610 (C4 (Web Text))

Max Activating Token Index: 246

Text #18

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0614. Min Act: -0.0004

Data Index: 1304630 (C4 (Web Text))

Max Activating Token Index: 516

Text #19

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0567. Min Act: -0.0004

Data Index: 678358 (C4 (Web Text))

Max Activating Token Index: 522