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

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

Neuron 2003 in Layer 0

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: 0.5646. Min Range: -0.5646

Max Act: 0.5646. Min Act: -0.0001

Data Index: 451126 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.5646. Min Range: -0.5646

Max Act: 0.5511. Min Act: -0.0001

Data Index: 452528 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.5646. Min Range: -0.5646

Max Act: 0.5477. Min Act: -0.0001

Data Index: 1194401 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.5646. Min Range: -0.5646

Max Act: 0.5477. Min Act: -0.0001

Data Index: 1009714 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.5646. Min Range: -0.5646

Max Act: 0.5425. Min Act: -0.0001

Data Index: 1320626 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.5646. Min Range: -0.5646

Max Act: 0.5366. Min Act: -0.0001

Data Index: 1538438 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.5646. Min Range: -0.5646

Max Act: 0.5277. Min Act: -0.0001

Data Index: 17376 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.5646. Min Range: -0.5646

Max Act: 0.5399. Min Act: -0.0001

Data Index: 189668 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.5646. Min Range: -0.5646

Max Act: 0.5381. Min Act: -0.0001

Data Index: 366714 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.5646. Min Range: -0.5646

Max Act: 0.5273. Min Act: -0.0001

Data Index: 420793 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.5646. Min Range: -0.5646

Max Act: 0.5311. Min Act: -0.0001

Data Index: 1333738 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.5646. Min Range: -0.5646

Max Act: 0.5326. Min Act: -0.0001

Data Index: 760601 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.5646. Min Range: -0.5646

Max Act: 0.5260. Min Act: -0.0001

Data Index: 99675 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.5646. Min Range: -0.5646

Max Act: 0.5217. Min Act: -0.0001

Data Index: 781342 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.5646. Min Range: -0.5646

Max Act: 0.5172. Min Act: -0.0001

Data Index: 917445 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.5646. Min Range: -0.5646

Max Act: 0.5183. Min Act: -0.0001

Data Index: 866629 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.5646. Min Range: -0.5646

Max Act: 0.5185. Min Act: -0.0001

Data Index: 478080 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.5646. Min Range: -0.5646

Max Act: 0.5178. Min Act: -0.0001

Data Index: 914916 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.5646. Min Range: -0.5646

Max Act: 0.5294. Min Act: -0.0001

Data Index: 1228386 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.5646. Min Range: -0.5646

Max Act: 0.5237. Min Act: -0.0001

Data Index: 576094 (C4 (Web Text))

Max Activating Token Index: 1023