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

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

Neuron 4318 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2267. Min Range: -2.2267

Max Act: 2.2267. Min Act: -0.0000

Data Index: 227785 (C4 (Web Text))

Max Activating Token Index: 832

Text #1

Max Range: 2.2267. Min Range: -2.2267

Max Act: 0.9474. Min Act: -0.0000

Data Index: 1279677 (C4 (Web Text))

Max Activating Token Index: 309

Text #2

Max Range: 2.2267. Min Range: -2.2267

Max Act: 0.9408. Min Act: -0.0000

Data Index: 385876 (C4 (Web Text))

Max Activating Token Index: 159

Text #3

Max Range: 2.2267. Min Range: -2.2267

Max Act: 0.9539. Min Act: -0.0000

Data Index: 437327 (C4 (Web Text))

Max Activating Token Index: 898

Text #4

Max Range: 2.2267. Min Range: -2.2267

Max Act: 1.0157. Min Act: -0.0000

Data Index: 139937 (C4 (Web Text))

Max Activating Token Index: 788

Text #5

Max Range: 2.2267. Min Range: -2.2267

Max Act: 0.8815. Min Act: -0.0000

Data Index: 407832 (C4 (Web Text))

Max Activating Token Index: 270

Text #6

Max Range: 2.2267. Min Range: -2.2267

Max Act: 0.9237. Min Act: -0.0000

Data Index: 1082757 (C4 (Web Text))

Max Activating Token Index: 333

Text #7

Max Range: 2.2267. Min Range: -2.2267

Max Act: 0.9179. Min Act: -0.0000

Data Index: 1167407 (C4 (Web Text))

Max Activating Token Index: 339

Text #8

Max Range: 2.2267. Min Range: -2.2267

Max Act: 0.7551. Min Act: -0.0000

Data Index: 137565 (C4 (Web Text))

Max Activating Token Index: 891

Text #9

Max Range: 2.2267. Min Range: -2.2267

Max Act: 0.8814. Min Act: -0.0000

Data Index: 968833 (C4 (Web Text))

Max Activating Token Index: 728

Text #10

Max Range: 2.2267. Min Range: -2.2267

Max Act: 0.8029. Min Act: -0.0000

Data Index: 573532 (C4 (Web Text))

Max Activating Token Index: 899

Text #11

Max Range: 2.2267. Min Range: -2.2267

Max Act: 0.8115. Min Act: -0.0000

Data Index: 100464 (C4 (Web Text))

Max Activating Token Index: 605

Text #12

Max Range: 2.2267. Min Range: -2.2267

Max Act: 0.7135. Min Act: -0.0000

Data Index: 1215872 (C4 (Web Text))

Max Activating Token Index: 141

Text #13

Max Range: 2.2267. Min Range: -2.2267

Max Act: 0.7877. Min Act: -0.0000

Data Index: 336086 (C4 (Web Text))

Max Activating Token Index: 487

Text #14

Max Range: 2.2267. Min Range: -2.2267

Max Act: 0.7868. Min Act: -0.0000

Data Index: 1313130 (C4 (Web Text))

Max Activating Token Index: 860

Text #15

Max Range: 2.2267. Min Range: -2.2267

Max Act: 0.7820. Min Act: -0.0000

Data Index: 325153 (C4 (Web Text))

Max Activating Token Index: 860

Text #16

Max Range: 2.2267. Min Range: -2.2267

Max Act: 0.7594. Min Act: -0.0000

Data Index: 1336705 (C4 (Web Text))

Max Activating Token Index: 693

Text #17

Max Range: 2.2267. Min Range: -2.2267

Max Act: 0.6878. Min Act: -0.0000

Data Index: 205710 (C4 (Web Text))

Max Activating Token Index: 926

Text #18

Max Range: 2.2267. Min Range: -2.2267

Max Act: 0.6827. Min Act: -0.0000

Data Index: 972093 (C4 (Web Text))

Max Activating Token Index: 852

Text #19

Max Range: 2.2267. Min Range: -2.2267

Max Act: 0.7291. Min Act: -0.0000

Data Index: 1280884 (C4 (Web Text))

Max Activating Token Index: 382