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

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

Neuron 1430 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: 2.2909. Min Range: -2.2909

Max Act: 2.2909. Min Act: -0.0003

Data Index: 409960 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 2.2909. Min Range: -2.2909

Max Act: 2.2837. Min Act: -0.0002

Data Index: 526666 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 2.2909. Min Range: -2.2909

Max Act: 2.1665. Min Act: -0.0002

Data Index: 1033352 (C4 (Web Text))

Max Activating Token Index: 421

Text #3

Max Range: 2.2909. Min Range: -2.2909

Max Act: 2.1737. Min Act: -0.0002

Data Index: 138236 (C4 (Web Text))

Max Activating Token Index: 103

Text #4

Max Range: 2.2909. Min Range: -2.2909

Max Act: 2.1563. Min Act: -0.0002

Data Index: 743567 (C4 (Web Text))

Max Activating Token Index: 321

Text #5

Max Range: 2.2909. Min Range: -2.2909

Max Act: 2.0618. Min Act: -0.0002

Data Index: 115289 (C4 (Web Text))

Max Activating Token Index: 250

Text #6

Max Range: 2.2909. Min Range: -2.2909

Max Act: 2.0702. Min Act: -0.0002

Data Index: 559437 (C4 (Web Text))

Max Activating Token Index: 685

Text #7

Max Range: 2.2909. Min Range: -2.2909

Max Act: 2.0641. Min Act: -0.0003

Data Index: 1286924 (C4 (Web Text))

Max Activating Token Index: 27

Text #8

Max Range: 2.2909. Min Range: -2.2909

Max Act: 2.0203. Min Act: -0.0002

Data Index: 555188 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 2.2909. Min Range: -2.2909

Max Act: 2.0358. Min Act: -0.0002

Data Index: 993944 (C4 (Web Text))

Max Activating Token Index: 15

Text #10

Max Range: 2.2909. Min Range: -2.2909

Max Act: 2.0651. Min Act: -0.0003

Data Index: 816211 (C4 (Web Text))

Max Activating Token Index: 528

Text #11

Max Range: 2.2909. Min Range: -2.2909

Max Act: 2.0149. Min Act: -0.0002

Data Index: 737411 (C4 (Web Text))

Max Activating Token Index: 41

Text #12

Max Range: 2.2909. Min Range: -2.2909

Max Act: 1.9806. Min Act: -0.0002

Data Index: 362835 (C4 (Web Text))

Max Activating Token Index: 430

Text #13

Max Range: 2.2909. Min Range: -2.2909

Max Act: 2.0454. Min Act: -0.0002

Data Index: 352546 (C4 (Web Text))

Max Activating Token Index: 455

Text #14

Max Range: 2.2909. Min Range: -2.2909

Max Act: 2.0176. Min Act: -0.0002

Data Index: 812936 (C4 (Web Text))

Max Activating Token Index: 65

Text #15

Max Range: 2.2909. Min Range: -2.2909

Max Act: 1.9634. Min Act: -0.0002

Data Index: 820568 (C4 (Web Text))

Max Activating Token Index: 99

Text #16

Max Range: 2.2909. Min Range: -2.2909

Max Act: 1.9173. Min Act: -0.0002

Data Index: 768719 (C4 (Web Text))

Max Activating Token Index: 81

Text #17

Max Range: 2.2909. Min Range: -2.2909

Max Act: 1.9584. Min Act: -0.0002

Data Index: 885903 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 2.2909. Min Range: -2.2909

Max Act: 1.9537. Min Act: -0.0002

Data Index: 1014946 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 2.2909. Min Range: -2.2909

Max Act: 1.9638. Min Act: -0.0003

Data Index: 813964 (C4 (Web Text))

Max Activating Token Index: 9