Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 348 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0957. Min Act: -0.0001

Data Index: 303769 (C4 (Web Text))

Max Activating Token Index: 519

Text #1

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0903. Min Act: -0.0001

Data Index: 318264 (C4 (Web Text))

Max Activating Token Index: 381

Text #2

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0893. Min Act: -0.0001

Data Index: 1160767 (C4 (Web Text))

Max Activating Token Index: 936

Text #3

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0862. Min Act: -0.0001

Data Index: 1311917 (C4 (Web Text))

Max Activating Token Index: 267

Text #4

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0858. Min Act: 0.0000

Data Index: 52749 (C4 (Web Text))

Max Activating Token Index: 187

Text #5

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0851. Min Act: -0.0001

Data Index: 1055929 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0834. Min Act: -0.0001

Data Index: 15623 (C4 (Web Text))

Max Activating Token Index: 289

Text #7

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0848. Min Act: -0.0001

Data Index: 1326132 (C4 (Web Text))

Max Activating Token Index: 331

Text #8

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0814. Min Act: -0.0001

Data Index: 862277 (C4 (Web Text))

Max Activating Token Index: 285

Text #9

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0803. Min Act: -0.0002

Data Index: 18859 (C4 (Web Text))

Max Activating Token Index: 31

Text #10

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0805. Min Act: -0.0002

Data Index: 818551 (C4 (Web Text))

Max Activating Token Index: 387

Text #11

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0805. Min Act: -0.0001

Data Index: 321663 (C4 (Web Text))

Max Activating Token Index: 441

Text #12

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0784. Min Act: -0.0002

Data Index: 1330575 (C4 (Web Text))

Max Activating Token Index: 821

Text #13

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0780. Min Act: -0.0001

Data Index: 1249933 (C4 (Web Text))

Max Activating Token Index: 448

Text #14

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0770. Min Act: -0.0001

Data Index: 991812 (C4 (Web Text))

Max Activating Token Index: 347

Text #15

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0753. Min Act: 0.0000

Data Index: 368221 (C4 (Web Text))

Max Activating Token Index: 722

Text #16

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0755. Min Act: -0.0001

Data Index: 166842 (C4 (Web Text))

Max Activating Token Index: 403

Text #17

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0750. Min Act: -0.0001

Data Index: 109923 (C4 (Web Text))

Max Activating Token Index: 583

Text #18

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0770. Min Act: -0.0002

Data Index: 1006204 (C4 (Web Text))

Max Activating Token Index: 261

Text #19

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0771. Min Act: -0.0001

Data Index: 221305 (C4 (Web Text))

Max Activating Token Index: 669