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

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

Neuron 434 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7080. Min Range: -0.7080

Max Act: 0.7080. Min Act: -0.0000

Data Index: 1013148 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 0.7080. Min Range: -0.7080

Max Act: 0.6911. Min Act: 0.0001

Data Index: 30782 (C4 (Web Text))

Max Activating Token Index: 196

Text #2

Max Range: 0.7080. Min Range: -0.7080

Max Act: 0.6333. Min Act: -0.0000

Data Index: 272808 (C4 (Web Text))

Max Activating Token Index: 86

Text #3

Max Range: 0.7080. Min Range: -0.7080

Max Act: 0.6061. Min Act: 0.0000

Data Index: 333013 (C4 (Web Text))

Max Activating Token Index: 168

Text #4

Max Range: 0.7080. Min Range: -0.7080

Max Act: 0.6021. Min Act: -0.0000

Data Index: 105997 (C4 (Web Text))

Max Activating Token Index: 356

Text #5

Max Range: 0.7080. Min Range: -0.7080

Max Act: 0.6005. Min Act: 0.0001

Data Index: 611899 (C4 (Web Text))

Max Activating Token Index: 212

Text #6

Max Range: 0.7080. Min Range: -0.7080

Max Act: 0.5699. Min Act: 0.0000

Data Index: 815215 (C4 (Web Text))

Max Activating Token Index: 167

Text #7

Max Range: 0.7080. Min Range: -0.7080

Max Act: 0.5732. Min Act: 0.0001

Data Index: 373501 (C4 (Web Text))

Max Activating Token Index: 925

Text #8

Max Range: 0.7080. Min Range: -0.7080

Max Act: 0.5694. Min Act: 0.0001

Data Index: 1145103 (C4 (Web Text))

Max Activating Token Index: 461

Text #9

Max Range: 0.7080. Min Range: -0.7080

Max Act: 0.5660. Min Act: 0.0000

Data Index: 952938 (C4 (Web Text))

Max Activating Token Index: 278

Text #10

Max Range: 0.7080. Min Range: -0.7080

Max Act: 0.5825. Min Act: 0.0001

Data Index: 342118 (C4 (Web Text))

Max Activating Token Index: 237

Text #11

Max Range: 0.7080. Min Range: -0.7080

Max Act: 0.5572. Min Act: -0.0000

Data Index: 909701 (C4 (Web Text))

Max Activating Token Index: 495

Text #12

Max Range: 0.7080. Min Range: -0.7080

Max Act: 0.5509. Min Act: 0.0001

Data Index: 1116620 (C4 (Web Text))

Max Activating Token Index: 108

Text #13

Max Range: 0.7080. Min Range: -0.7080

Max Act: 0.5520. Min Act: -0.0000

Data Index: 348328 (C4 (Web Text))

Max Activating Token Index: 879

Text #14

Max Range: 0.7080. Min Range: -0.7080

Max Act: 0.5532. Min Act: 0.0001

Data Index: 318449 (C4 (Web Text))

Max Activating Token Index: 171

Text #15

Max Range: 0.7080. Min Range: -0.7080

Max Act: 0.5514. Min Act: -0.0000

Data Index: 944696 (C4 (Web Text))

Max Activating Token Index: 86

Text #16

Max Range: 0.7080. Min Range: -0.7080

Max Act: 0.5662. Min Act: -0.0000

Data Index: 702256 (C4 (Web Text))

Max Activating Token Index: 603

Text #17

Max Range: 0.7080. Min Range: -0.7080

Max Act: 0.5324. Min Act: 0.0000

Data Index: 557511 (C4 (Web Text))

Max Activating Token Index: 388

Text #18

Max Range: 0.7080. Min Range: -0.7080

Max Act: 0.5322. Min Act: -0.0000

Data Index: 997430 (C4 (Web Text))

Max Activating Token Index: 762

Text #19

Max Range: 0.7080. Min Range: -0.7080

Max Act: 0.5347. Min Act: 0.0001

Data Index: 559 (C4 (Web Text))

Max Activating Token Index: 203