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

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

Neuron 3032 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1485. Min Range: -1.1485

Max Act: 1.1485. Min Act: -0.0001

Data Index: 93679 (C4 (Web Text))

Max Activating Token Index: 961

Text #1

Max Range: 1.1485. Min Range: -1.1485

Max Act: 1.0904. Min Act: -0.0002

Data Index: 55757 (C4 (Web Text))

Max Activating Token Index: 797

Text #2

Max Range: 1.1485. Min Range: -1.1485

Max Act: 1.0866. Min Act: -0.0001

Data Index: 203433 (C4 (Web Text))

Max Activating Token Index: 1005

Text #3

Max Range: 1.1485. Min Range: -1.1485

Max Act: 1.0149. Min Act: -0.0001

Data Index: 1034006 (C4 (Web Text))

Max Activating Token Index: 956

Text #4

Max Range: 1.1485. Min Range: -1.1485

Max Act: 1.0347. Min Act: -0.0002

Data Index: 224401 (C4 (Web Text))

Max Activating Token Index: 894

Text #5

Max Range: 1.1485. Min Range: -1.1485

Max Act: 1.0317. Min Act: -0.0002

Data Index: 447521 (C4 (Web Text))

Max Activating Token Index: 700

Text #6

Max Range: 1.1485. Min Range: -1.1485

Max Act: 1.0931. Min Act: -0.0001

Data Index: 837091 (C4 (Web Text))

Max Activating Token Index: 919

Text #7

Max Range: 1.1485. Min Range: -1.1485

Max Act: 1.1045. Min Act: -0.0001

Data Index: 566872 (C4 (Web Text))

Max Activating Token Index: 821

Text #8

Max Range: 1.1485. Min Range: -1.1485

Max Act: 1.0121. Min Act: -0.0001

Data Index: 711334 (C4 (Web Text))

Max Activating Token Index: 980

Text #9

Max Range: 1.1485. Min Range: -1.1485

Max Act: 0.9832. Min Act: -0.0002

Data Index: 652634 (C4 (Web Text))

Max Activating Token Index: 944

Text #10

Max Range: 1.1485. Min Range: -1.1485

Max Act: 0.9703. Min Act: -0.0001

Data Index: 1098770 (C4 (Web Text))

Max Activating Token Index: 523

Text #11

Max Range: 1.1485. Min Range: -1.1485

Max Act: 0.9617. Min Act: -0.0002

Data Index: 1243546 (C4 (Web Text))

Max Activating Token Index: 480

Text #12

Max Range: 1.1485. Min Range: -1.1485

Max Act: 0.9875. Min Act: -0.0002

Data Index: 640414 (C4 (Web Text))

Max Activating Token Index: 452

Text #13

Max Range: 1.1485. Min Range: -1.1485

Max Act: 1.0143. Min Act: -0.0002

Data Index: 620576 (C4 (Web Text))

Max Activating Token Index: 486

Text #14

Max Range: 1.1485. Min Range: -1.1485

Max Act: 1.0157. Min Act: -0.0001

Data Index: 19982 (C4 (Web Text))

Max Activating Token Index: 444

Text #15

Max Range: 1.1485. Min Range: -1.1485

Max Act: 0.9638. Min Act: -0.0002

Data Index: 613565 (C4 (Web Text))

Max Activating Token Index: 859

Text #16

Max Range: 1.1485. Min Range: -1.1485

Max Act: 1.0453. Min Act: -0.0002

Data Index: 1341 (C4 (Web Text))

Max Activating Token Index: 457

Text #17

Max Range: 1.1485. Min Range: -1.1485

Max Act: 0.9514. Min Act: -0.0002

Data Index: 870921 (C4 (Web Text))

Max Activating Token Index: 653

Text #18

Max Range: 1.1485. Min Range: -1.1485

Max Act: 0.9749. Min Act: -0.0002

Data Index: 364619 (C4 (Web Text))

Max Activating Token Index: 689

Text #19

Max Range: 1.1485. Min Range: -1.1485

Max Act: 0.9269. Min Act: -0.0002

Data Index: 351144 (C4 (Web Text))

Max Activating Token Index: 711