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

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

Neuron 4653 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9209. Min Range: -2.9209

Max Act: 2.7674. Min Act: -0.0000

Data Index: 539667 (C4 (Web Text))

Max Activating Token Index: 419

Text #1

Max Range: 2.9209. Min Range: -2.9209

Max Act: 2.9209. Min Act: -0.0000

Data Index: 32263 (C4 (Web Text))

Max Activating Token Index: 890

Text #2

Max Range: 2.9209. Min Range: -2.9209

Max Act: 2.5867. Min Act: -0.0000

Data Index: 459601 (C4 (Web Text))

Max Activating Token Index: 301

Text #3

Max Range: 2.9209. Min Range: -2.9209

Max Act: 2.6884. Min Act: -0.0001

Data Index: 107006 (C4 (Web Text))

Max Activating Token Index: 253

Text #4

Max Range: 2.9209. Min Range: -2.9209

Max Act: 2.5757. Min Act: -0.0000

Data Index: 1242574 (C4 (Web Text))

Max Activating Token Index: 63

Text #5

Max Range: 2.9209. Min Range: -2.9209

Max Act: 2.6946. Min Act: -0.0000

Data Index: 235802 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 2.9209. Min Range: -2.9209

Max Act: 2.5468. Min Act: -0.0000

Data Index: 1097476 (C4 (Web Text))

Max Activating Token Index: 54

Text #7

Max Range: 2.9209. Min Range: -2.9209

Max Act: 2.5018. Min Act: -0.0000

Data Index: 1284772 (C4 (Web Text))

Max Activating Token Index: 6

Text #8

Max Range: 2.9209. Min Range: -2.9209

Max Act: 2.4798. Min Act: -0.0000

Data Index: 708310 (C4 (Web Text))

Max Activating Token Index: 754

Text #9

Max Range: 2.9209. Min Range: -2.9209

Max Act: 2.4701. Min Act: -0.0001

Data Index: 994494 (C4 (Web Text))

Max Activating Token Index: 419

Text #10

Max Range: 2.9209. Min Range: -2.9209

Max Act: 2.5666. Min Act: -0.0000

Data Index: 206806 (C4 (Web Text))

Max Activating Token Index: 937

Text #11

Max Range: 2.9209. Min Range: -2.9209

Max Act: 2.2072. Min Act: -0.0001

Data Index: 1347274 (C4 (Web Text))

Max Activating Token Index: 836

Text #12

Max Range: 2.9209. Min Range: -2.9209

Max Act: 2.3157. Min Act: -0.0000

Data Index: 522025 (C4 (Web Text))

Max Activating Token Index: 846

Text #13

Max Range: 2.9209. Min Range: -2.9209

Max Act: 2.0743. Min Act: -0.0001

Data Index: 594398 (C4 (Web Text))

Max Activating Token Index: 800

Text #14

Max Range: 2.9209. Min Range: -2.9209

Max Act: 2.3255. Min Act: -0.0001

Data Index: 487152 (C4 (Web Text))

Max Activating Token Index: 167

Text #15

Max Range: 2.9209. Min Range: -2.9209

Max Act: 2.3243. Min Act: -0.0001

Data Index: 1030167 (C4 (Web Text))

Max Activating Token Index: 176

Text #16

Max Range: 2.9209. Min Range: -2.9209

Max Act: 2.4875. Min Act: -0.0000

Data Index: 62596 (C4 (Web Text))

Max Activating Token Index: 295

Text #17

Max Range: 2.9209. Min Range: -2.9209

Max Act: 2.2650. Min Act: -0.0000

Data Index: 461273 (C4 (Web Text))

Max Activating Token Index: 708

Text #18

Max Range: 2.9209. Min Range: -2.9209

Max Act: 2.3792. Min Act: -0.0000

Data Index: 80484 (C4 (Web Text))

Max Activating Token Index: 823

Text #19

Max Range: 2.9209. Min Range: -2.9209

Max Act: 2.2670. Min Act: -0.0001

Data Index: 145305 (C4 (Web Text))

Max Activating Token Index: 235