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

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

Neuron 4184 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8597. Min Range: -1.8597

Max Act: 1.8597. Min Act: -0.0000

Data Index: 806043 (C4 (Web Text))

Max Activating Token Index: 75

Text #1

Max Range: 1.8597. Min Range: -1.8597

Max Act: 1.5612. Min Act: -0.0000

Data Index: 1093756 (C4 (Web Text))

Max Activating Token Index: 115

Text #2

Max Range: 1.8597. Min Range: -1.8597

Max Act: 1.1077. Min Act: -0.0000

Data Index: 1277452 (C4 (Web Text))

Max Activating Token Index: 360

Text #3

Max Range: 1.8597. Min Range: -1.8597

Max Act: 1.3823. Min Act: -0.0000

Data Index: 491942 (C4 (Web Text))

Max Activating Token Index: 352

Text #4

Max Range: 1.8597. Min Range: -1.8597

Max Act: 1.1367. Min Act: -0.0000

Data Index: 329487 (C4 (Web Text))

Max Activating Token Index: 275

Text #5

Max Range: 1.8597. Min Range: -1.8597

Max Act: 1.2187. Min Act: -0.0000

Data Index: 979656 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 1.8597. Min Range: -1.8597

Max Act: 1.3283. Min Act: -0.0001

Data Index: 432193 (C4 (Web Text))

Max Activating Token Index: 398

Text #7

Max Range: 1.8597. Min Range: -1.8597

Max Act: 1.2210. Min Act: -0.0000

Data Index: 946375 (C4 (Web Text))

Max Activating Token Index: 289

Text #8

Max Range: 1.8597. Min Range: -1.8597

Max Act: 1.1673. Min Act: -0.0000

Data Index: 422067 (C4 (Web Text))

Max Activating Token Index: 970

Text #9

Max Range: 1.8597. Min Range: -1.8597

Max Act: 1.3127. Min Act: -0.0000

Data Index: 861656 (C4 (Web Text))

Max Activating Token Index: 446

Text #10

Max Range: 1.8597. Min Range: -1.8597

Max Act: 1.2796. Min Act: -0.0000

Data Index: 1273375 (C4 (Web Text))

Max Activating Token Index: 118

Text #11

Max Range: 1.8597. Min Range: -1.8597

Max Act: 1.1825. Min Act: -0.0000

Data Index: 232006 (C4 (Web Text))

Max Activating Token Index: 963

Text #12

Max Range: 1.8597. Min Range: -1.8597

Max Act: 1.1997. Min Act: -0.0000

Data Index: 1124980 (C4 (Web Text))

Max Activating Token Index: 420

Text #13

Max Range: 1.8597. Min Range: -1.8597

Max Act: 1.1929. Min Act: -0.0000

Data Index: 218294 (C4 (Web Text))

Max Activating Token Index: 482

Text #14

Max Range: 1.8597. Min Range: -1.8597

Max Act: 1.0436. Min Act: -0.0001

Data Index: 93812 (C4 (Web Text))

Max Activating Token Index: 321

Text #15

Max Range: 1.8597. Min Range: -1.8597

Max Act: 1.1693. Min Act: -0.0000

Data Index: 832499 (C4 (Web Text))

Max Activating Token Index: 896

Text #16

Max Range: 1.8597. Min Range: -1.8597

Max Act: 1.1309. Min Act: -0.0000

Data Index: 937175 (C4 (Web Text))

Max Activating Token Index: 433

Text #17

Max Range: 1.8597. Min Range: -1.8597

Max Act: 1.1775. Min Act: -0.0000

Data Index: 730571 (C4 (Web Text))

Max Activating Token Index: 596

Text #18

Max Range: 1.8597. Min Range: -1.8597

Max Act: 1.1045. Min Act: -0.0000

Data Index: 432747 (C4 (Web Text))

Max Activating Token Index: 451

Text #19

Max Range: 1.8597. Min Range: -1.8597

Max Act: 1.0932. Min Act: -0.0000

Data Index: 839476 (C4 (Web Text))

Max Activating Token Index: 509