Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2188 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.8728. Min Range: -0.8728

Max Act: 0.7464. Min Act: -0.0001

Data Index: 51426 (C4 (Web Text))

Max Activating Token Index: 306

Text #1

Max Range: 0.8728. Min Range: -0.8728

Max Act: 0.8728. Min Act: -0.0001

Data Index: 944149 (C4 (Web Text))

Max Activating Token Index: 24

Text #2

Max Range: 0.8728. Min Range: -0.8728

Max Act: 0.7627. Min Act: -0.0001

Data Index: 206330 (C4 (Web Text))

Max Activating Token Index: 58

Text #3

Max Range: 0.8728. Min Range: -0.8728

Max Act: 0.7795. Min Act: -0.0001

Data Index: 967990 (C4 (Web Text))

Max Activating Token Index: 237

Text #4

Max Range: 0.8728. Min Range: -0.8728

Max Act: 0.7715. Min Act: -0.0001

Data Index: 492863 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 0.8728. Min Range: -0.8728

Max Act: 0.7035. Min Act: -0.0001

Data Index: 27250 (C4 (Web Text))

Max Activating Token Index: 597

Text #6

Max Range: 0.8728. Min Range: -0.8728

Max Act: 0.7606. Min Act: -0.0001

Data Index: 283652 (C4 (Web Text))

Max Activating Token Index: 962

Text #7

Max Range: 0.8728. Min Range: -0.8728

Max Act: 0.7636. Min Act: -0.0001

Data Index: 104929 (C4 (Web Text))

Max Activating Token Index: 374

Text #8

Max Range: 0.8728. Min Range: -0.8728

Max Act: 0.7366. Min Act: -0.0001

Data Index: 1007265 (C4 (Web Text))

Max Activating Token Index: 70

Text #9

Max Range: 0.8728. Min Range: -0.8728

Max Act: 0.7639. Min Act: -0.0001

Data Index: 827991 (C4 (Web Text))

Max Activating Token Index: 773

Text #10

Max Range: 0.8728. Min Range: -0.8728

Max Act: 0.7655. Min Act: -0.0001

Data Index: 458684 (C4 (Web Text))

Max Activating Token Index: 957

Text #11

Max Range: 0.8728. Min Range: -0.8728

Max Act: 0.7065. Min Act: -0.0001

Data Index: 491955 (C4 (Web Text))

Max Activating Token Index: 231

Text #12

Max Range: 0.8728. Min Range: -0.8728

Max Act: 0.7051. Min Act: -0.0001

Data Index: 365429 (C4 (Web Text))

Max Activating Token Index: 56

Text #13

Max Range: 0.8728. Min Range: -0.8728

Max Act: 0.6337. Min Act: -0.0001

Data Index: 695847 (C4 (Web Text))

Max Activating Token Index: 305

Text #14

Max Range: 0.8728. Min Range: -0.8728

Max Act: 0.7132. Min Act: -0.0001

Data Index: 296505 (C4 (Web Text))

Max Activating Token Index: 697

Text #15

Max Range: 0.8728. Min Range: -0.8728

Max Act: 0.6984. Min Act: -0.0001

Data Index: 872262 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 0.8728. Min Range: -0.8728

Max Act: 0.6889. Min Act: -0.0001

Data Index: 436119 (C4 (Web Text))

Max Activating Token Index: 650

Text #17

Max Range: 0.8728. Min Range: -0.8728

Max Act: 0.6832. Min Act: -0.0001

Data Index: 733454 (C4 (Web Text))

Max Activating Token Index: 533

Text #18

Max Range: 0.8728. Min Range: -0.8728

Max Act: 0.6849. Min Act: -0.0001

Data Index: 1034726 (C4 (Web Text))

Max Activating Token Index: 466

Text #19

Max Range: 0.8728. Min Range: -0.8728

Max Act: 0.7014. Min Act: -0.0001

Data Index: 1330795 (C4 (Web Text))

Max Activating Token Index: 204