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

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

Neuron 3314 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 2.0943. Min Range: -2.0943

Max Act: 2.0943. Min Act: -0.0002

Data Index: 960138 (C4 (Web Text))

Max Activating Token Index: 691

Text #1

Max Range: 2.0943. Min Range: -2.0943

Max Act: 1.8766. Min Act: -0.0002

Data Index: 397452 (C4 (Web Text))

Max Activating Token Index: 130

Text #2

Max Range: 2.0943. Min Range: -2.0943

Max Act: 1.8898. Min Act: -0.0002

Data Index: 509818 (C4 (Web Text))

Max Activating Token Index: 502

Text #3

Max Range: 2.0943. Min Range: -2.0943

Max Act: 1.7836. Min Act: -0.0002

Data Index: 375590 (C4 (Web Text))

Max Activating Token Index: 599

Text #4

Max Range: 2.0943. Min Range: -2.0943

Max Act: 1.7972. Min Act: -0.0002

Data Index: 234708 (C4 (Web Text))

Max Activating Token Index: 861

Text #5

Max Range: 2.0943. Min Range: -2.0943

Max Act: 1.8031. Min Act: -0.0002

Data Index: 603073 (C4 (Web Text))

Max Activating Token Index: 589

Text #6

Max Range: 2.0943. Min Range: -2.0943

Max Act: 1.7056. Min Act: -0.0002

Data Index: 952430 (C4 (Web Text))

Max Activating Token Index: 868

Text #7

Max Range: 2.0943. Min Range: -2.0943

Max Act: 1.6904. Min Act: -0.0002

Data Index: 93769 (C4 (Web Text))

Max Activating Token Index: 871

Text #8

Max Range: 2.0943. Min Range: -2.0943

Max Act: 1.6680. Min Act: -0.0002

Data Index: 691813 (C4 (Web Text))

Max Activating Token Index: 621

Text #9

Max Range: 2.0943. Min Range: -2.0943

Max Act: 1.6291. Min Act: -0.0002

Data Index: 122896 (C4 (Web Text))

Max Activating Token Index: 561

Text #10

Max Range: 2.0943. Min Range: -2.0943

Max Act: 1.6155. Min Act: -0.0002

Data Index: 743941 (C4 (Web Text))

Max Activating Token Index: 757

Text #11

Max Range: 2.0943. Min Range: -2.0943

Max Act: 1.6505. Min Act: -0.0002

Data Index: 884378 (C4 (Web Text))

Max Activating Token Index: 850

Text #12

Max Range: 2.0943. Min Range: -2.0943

Max Act: 1.6310. Min Act: -0.0002

Data Index: 523830 (C4 (Web Text))

Max Activating Token Index: 776

Text #13

Max Range: 2.0943. Min Range: -2.0943

Max Act: 1.5807. Min Act: -0.0002

Data Index: 512877 (C4 (Web Text))

Max Activating Token Index: 424

Text #14

Max Range: 2.0943. Min Range: -2.0943

Max Act: 1.5736. Min Act: -0.0002

Data Index: 1306816 (C4 (Web Text))

Max Activating Token Index: 85

Text #15

Max Range: 2.0943. Min Range: -2.0943

Max Act: 1.6425. Min Act: -0.0002

Data Index: 999236 (C4 (Web Text))

Max Activating Token Index: 751

Text #16

Max Range: 2.0943. Min Range: -2.0943

Max Act: 1.5742. Min Act: -0.0002

Data Index: 1020866 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 2.0943. Min Range: -2.0943

Max Act: 1.5940. Min Act: -0.0002

Data Index: 1165432 (C4 (Web Text))

Max Activating Token Index: 416

Text #18

Max Range: 2.0943. Min Range: -2.0943

Max Act: 1.5455. Min Act: -0.0002

Data Index: 357636 (C4 (Web Text))

Max Activating Token Index: 727

Text #19

Max Range: 2.0943. Min Range: -2.0943

Max Act: 1.5413. Min Act: -0.0002

Data Index: 815046 (C4 (Web Text))

Max Activating Token Index: 569