Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3964 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.1001. Min Act: -0.0001

Data Index: 340673 (C4 (Web Text))

Max Activating Token Index: 825

Text #1

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0919. Min Act: -0.0001

Data Index: 1597901 (Python Code)

Max Activating Token Index: 631

Text #2

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0983. Min Act: -0.0001

Data Index: 696502 (C4 (Web Text))

Max Activating Token Index: 325

Text #3

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0942. Min Act: -0.0001

Data Index: 271977 (C4 (Web Text))

Max Activating Token Index: 386

Text #4

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0877. Min Act: -0.0001

Data Index: 495156 (C4 (Web Text))

Max Activating Token Index: 163

Text #5

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0888. Min Act: -0.0001

Data Index: 1400903 (Python Code)

Max Activating Token Index: 179

Text #6

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0876. Min Act: -0.0001

Data Index: 341858 (C4 (Web Text))

Max Activating Token Index: 938

Text #7

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0854. Min Act: -0.0001

Data Index: 944229 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0867. Min Act: -0.0001

Data Index: 560466 (C4 (Web Text))

Max Activating Token Index: 209

Text #9

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0855. Min Act: -0.0001

Data Index: 249411 (C4 (Web Text))

Max Activating Token Index: 207

Text #10

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0849. Min Act: -0.0001

Data Index: 1192488 (C4 (Web Text))

Max Activating Token Index: 503

Text #11

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0738. Min Act: -0.0001

Data Index: 727671 (C4 (Web Text))

Max Activating Token Index: 607

Text #12

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0906. Min Act: -0.0001

Data Index: 1011685 (C4 (Web Text))

Max Activating Token Index: 327

Text #13

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0840. Min Act: -0.0001

Data Index: 1143637 (C4 (Web Text))

Max Activating Token Index: 471

Text #14

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0805. Min Act: -0.0001

Data Index: 1523117 (Python Code)

Max Activating Token Index: 374

Text #15

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0826. Min Act: -0.0001

Data Index: 1201756 (C4 (Web Text))

Max Activating Token Index: 155

Text #16

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0813. Min Act: -0.0001

Data Index: 709182 (C4 (Web Text))

Max Activating Token Index: 467

Text #17

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0784. Min Act: -0.0001

Data Index: 309469 (C4 (Web Text))

Max Activating Token Index: 408

Text #18

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0805. Min Act: -0.0001

Data Index: 963476 (C4 (Web Text))

Max Activating Token Index: 379

Text #19

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0775. Min Act: -0.0001

Data Index: 1355593 (C4 (Web Text))

Max Activating Token Index: 847