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

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

Neuron 4077 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: 0.0195. Min Range: -0.0195

Max Act: 0.0194. Min Act: -0.0001

Data Index: 803309 (C4 (Web Text))

Max Activating Token Index: 3

Text #1

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0194. Min Act: -0.0001

Data Index: 914840 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0194. Min Act: -0.0001

Data Index: 1115567 (C4 (Web Text))

Max Activating Token Index: 2

Text #3

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0194. Min Act: -0.0001

Data Index: 678635 (C4 (Web Text))

Max Activating Token Index: 2

Text #4

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0194. Min Act: -0.0001

Data Index: 434742 (C4 (Web Text))

Max Activating Token Index: 2

Text #5

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0194. Min Act: -0.0001

Data Index: 415797 (C4 (Web Text))

Max Activating Token Index: 2

Text #6

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0194. Min Act: -0.0001

Data Index: 338564 (C4 (Web Text))

Max Activating Token Index: 2

Text #7

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0194. Min Act: -0.0001

Data Index: 466440 (C4 (Web Text))

Max Activating Token Index: 2

Text #8

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0194. Min Act: -0.0001

Data Index: 1127981 (C4 (Web Text))

Max Activating Token Index: 2

Text #9

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0194. Min Act: -0.0001

Data Index: 1259388 (C4 (Web Text))

Max Activating Token Index: 2

Text #10

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0191. Min Act: -0.0001

Data Index: 1254613 (C4 (Web Text))

Max Activating Token Index: 2

Text #11

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0195. Min Act: -0.0001

Data Index: 721475 (C4 (Web Text))

Max Activating Token Index: 4

Text #12

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0194. Min Act: -0.0001

Data Index: 1109403 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0193. Min Act: -0.0001

Data Index: 276576 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0189. Min Act: -0.0001

Data Index: 956122 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0189. Min Act: -0.0001

Data Index: 58358 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0184. Min Act: -0.0001

Data Index: 994466 (C4 (Web Text))

Max Activating Token Index: 660

Text #17

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0184. Min Act: -0.0001

Data Index: 999638 (C4 (Web Text))

Max Activating Token Index: 7

Text #18

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0186. Min Act: -0.0001

Data Index: 1322344 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0186. Min Act: -0.0001

Data Index: 79745 (C4 (Web Text))

Max Activating Token Index: 6