Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2213 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.9831. Min Act: -0.0001

Data Index: 788474 (C4 (Web Text))

Max Activating Token Index: 684

Text #1

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.9950. Min Act: -0.0000

Data Index: 1162068 (C4 (Web Text))

Max Activating Token Index: 717

Text #2

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.9002. Min Act: -0.0000

Data Index: 426069 (C4 (Web Text))

Max Activating Token Index: 907

Text #3

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.9065. Min Act: -0.0001

Data Index: 459396 (C4 (Web Text))

Max Activating Token Index: 784

Text #4

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.8169. Min Act: -0.0000

Data Index: 227144 (C4 (Web Text))

Max Activating Token Index: 607

Text #5

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.8146. Min Act: -0.0000

Data Index: 210098 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.8042. Min Act: -0.0000

Data Index: 843462 (C4 (Web Text))

Max Activating Token Index: 208

Text #7

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.8022. Min Act: -0.0000

Data Index: 1009949 (C4 (Web Text))

Max Activating Token Index: 962

Text #8

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.7719. Min Act: -0.0000

Data Index: 854439 (C4 (Web Text))

Max Activating Token Index: 387

Text #9

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.7471. Min Act: -0.0000

Data Index: 32200 (C4 (Web Text))

Max Activating Token Index: 678

Text #10

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.8474. Min Act: -0.0000

Data Index: 31925 (C4 (Web Text))

Max Activating Token Index: 874

Text #11

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.7582. Min Act: -0.0000

Data Index: 874441 (C4 (Web Text))

Max Activating Token Index: 376

Text #12

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.7581. Min Act: -0.0001

Data Index: 326301 (C4 (Web Text))

Max Activating Token Index: 462

Text #13

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.7483. Min Act: -0.0000

Data Index: 844916 (C4 (Web Text))

Max Activating Token Index: 564

Text #14

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.8017. Min Act: -0.0001

Data Index: 225850 (C4 (Web Text))

Max Activating Token Index: 769

Text #15

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.7744. Min Act: -0.0001

Data Index: 274300 (C4 (Web Text))

Max Activating Token Index: 107

Text #16

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.7713. Min Act: -0.0000

Data Index: 32902 (C4 (Web Text))

Max Activating Token Index: 330

Text #17

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.7246. Min Act: -0.0000

Data Index: 249522 (C4 (Web Text))

Max Activating Token Index: 487

Text #18

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.7369. Min Act: -0.0000

Data Index: 982805 (C4 (Web Text))

Max Activating Token Index: 722

Text #19

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.7846. Min Act: -0.0001

Data Index: 1034693 (C4 (Web Text))

Max Activating Token Index: 339