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

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

Neuron 4415 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: 0.7535. Min Range: -0.7535

Max Act: 0.7535. Min Act: -0.0002

Data Index: 163983 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 0.7535. Min Range: -0.7535

Max Act: 0.7535. Min Act: -0.0002

Data Index: 487407 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 0.7535. Min Range: -0.7535

Max Act: 0.7535. Min Act: -0.0002

Data Index: 1181479 (C4 (Web Text))

Max Activating Token Index: 2

Text #3

Max Range: 0.7535. Min Range: -0.7535

Max Act: 0.6747. Min Act: -0.0002

Data Index: 826389 (C4 (Web Text))

Max Activating Token Index: 822

Text #4

Max Range: 0.7535. Min Range: -0.7535

Max Act: 0.6797. Min Act: -0.0002

Data Index: 1127964 (C4 (Web Text))

Max Activating Token Index: 3

Text #5

Max Range: 0.7535. Min Range: -0.7535

Max Act: 0.6797. Min Act: -0.0002

Data Index: 750525 (C4 (Web Text))

Max Activating Token Index: 3

Text #6

Max Range: 0.7535. Min Range: -0.7535

Max Act: 0.6496. Min Act: -0.0002

Data Index: 711811 (C4 (Web Text))

Max Activating Token Index: 19

Text #7

Max Range: 0.7535. Min Range: -0.7535

Max Act: 0.6534. Min Act: -0.0002

Data Index: 347084 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 0.7535. Min Range: -0.7535

Max Act: 0.6471. Min Act: -0.0002

Data Index: 276794 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 0.7535. Min Range: -0.7535

Max Act: 0.6228. Min Act: -0.0002

Data Index: 357744 (C4 (Web Text))

Max Activating Token Index: 3

Text #10

Max Range: 0.7535. Min Range: -0.7535

Max Act: 0.6070. Min Act: -0.0002

Data Index: 940572 (C4 (Web Text))

Max Activating Token Index: 7

Text #11

Max Range: 0.7535. Min Range: -0.7535

Max Act: 0.6176. Min Act: -0.0002

Data Index: 208596 (C4 (Web Text))

Max Activating Token Index: 3

Text #12

Max Range: 0.7535. Min Range: -0.7535

Max Act: 0.6097. Min Act: -0.0002

Data Index: 699234 (C4 (Web Text))

Max Activating Token Index: 827

Text #13

Max Range: 0.7535. Min Range: -0.7535

Max Act: 0.6052. Min Act: -0.0002

Data Index: 7912 (C4 (Web Text))

Max Activating Token Index: 641

Text #14

Max Range: 0.7535. Min Range: -0.7535

Max Act: 0.6149. Min Act: -0.0002

Data Index: 690585 (C4 (Web Text))

Max Activating Token Index: 270

Text #15

Max Range: 0.7535. Min Range: -0.7535

Max Act: 0.5870. Min Act: -0.0002

Data Index: 786963 (C4 (Web Text))

Max Activating Token Index: 803

Text #16

Max Range: 0.7535. Min Range: -0.7535

Max Act: 0.5966. Min Act: -0.0002

Data Index: 491053 (C4 (Web Text))

Max Activating Token Index: 914

Text #17

Max Range: 0.7535. Min Range: -0.7535

Max Act: 0.6075. Min Act: -0.0002

Data Index: 337106 (C4 (Web Text))

Max Activating Token Index: 11

Text #18

Max Range: 0.7535. Min Range: -0.7535

Max Act: 0.5999. Min Act: -0.0002

Data Index: 1016247 (C4 (Web Text))

Max Activating Token Index: 9

Text #19

Max Range: 0.7535. Min Range: -0.7535

Max Act: 0.6014. Min Act: -0.0002

Data Index: 945836 (C4 (Web Text))

Max Activating Token Index: 591