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

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

Neuron 2001 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0690. Min Act: -0.0002

Data Index: 503605 (C4 (Web Text))

Max Activating Token Index: 208

Text #1

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0676. Min Act: -0.0002

Data Index: 81183 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0653. Min Act: -0.0002

Data Index: 895569 (C4 (Web Text))

Max Activating Token Index: 133

Text #3

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0642. Min Act: -0.0002

Data Index: 1184025 (C4 (Web Text))

Max Activating Token Index: 615

Text #4

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0642. Min Act: -0.0002

Data Index: 195645 (C4 (Web Text))

Max Activating Token Index: 96

Text #5

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0641. Min Act: -0.0002

Data Index: 1166904 (C4 (Web Text))

Max Activating Token Index: 375

Text #6

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0639. Min Act: -0.0002

Data Index: 549221 (C4 (Web Text))

Max Activating Token Index: 403

Text #7

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0633. Min Act: -0.0002

Data Index: 1307797 (C4 (Web Text))

Max Activating Token Index: 221

Text #8

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0630. Min Act: -0.0002

Data Index: 645919 (C4 (Web Text))

Max Activating Token Index: 124

Text #9

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0629. Min Act: -0.0002

Data Index: 334213 (C4 (Web Text))

Max Activating Token Index: 394

Text #10

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0627. Min Act: -0.0002

Data Index: 1237915 (C4 (Web Text))

Max Activating Token Index: 142

Text #11

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0623. Min Act: -0.0002

Data Index: 1263642 (C4 (Web Text))

Max Activating Token Index: 267

Text #12

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0615. Min Act: -0.0002

Data Index: 417989 (C4 (Web Text))

Max Activating Token Index: 769

Text #13

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0614. Min Act: -0.0002

Data Index: 946901 (C4 (Web Text))

Max Activating Token Index: 190

Text #14

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0614. Min Act: -0.0002

Data Index: 1300321 (C4 (Web Text))

Max Activating Token Index: 379

Text #15

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0612. Min Act: -0.0002

Data Index: 140320 (C4 (Web Text))

Max Activating Token Index: 203

Text #16

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0610. Min Act: -0.0002

Data Index: 1286531 (C4 (Web Text))

Max Activating Token Index: 133

Text #17

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0610. Min Act: -0.0002

Data Index: 441239 (C4 (Web Text))

Max Activating Token Index: 575

Text #18

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0609. Min Act: -0.0002

Data Index: 1271278 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0609. Min Act: -0.0002

Data Index: 163152 (C4 (Web Text))

Max Activating Token Index: 75