Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1074 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.9750. Min Range: -1.9750

Max Act: 1.9750. Min Act: -0.0000

Data Index: 246975 (C4 (Web Text))

Max Activating Token Index: 159

Text #1

Max Range: 1.9750. Min Range: -1.9750

Max Act: 1.8559. Min Act: -0.0000

Data Index: 787221 (C4 (Web Text))

Max Activating Token Index: 1022

Text #2

Max Range: 1.9750. Min Range: -1.9750

Max Act: 1.7447. Min Act: -0.0000

Data Index: 751937 (C4 (Web Text))

Max Activating Token Index: 443

Text #3

Max Range: 1.9750. Min Range: -1.9750

Max Act: 1.6778. Min Act: -0.0000

Data Index: 590408 (C4 (Web Text))

Max Activating Token Index: 907

Text #4

Max Range: 1.9750. Min Range: -1.9750

Max Act: 1.4655. Min Act: -0.0000

Data Index: 1263379 (C4 (Web Text))

Max Activating Token Index: 364

Text #5

Max Range: 1.9750. Min Range: -1.9750

Max Act: 1.4660. Min Act: -0.0000

Data Index: 806708 (C4 (Web Text))

Max Activating Token Index: 266

Text #6

Max Range: 1.9750. Min Range: -1.9750

Max Act: 1.4055. Min Act: -0.0000

Data Index: 1075899 (C4 (Web Text))

Max Activating Token Index: 219

Text #7

Max Range: 1.9750. Min Range: -1.9750

Max Act: 1.3072. Min Act: -0.0000

Data Index: 336446 (C4 (Web Text))

Max Activating Token Index: 439

Text #8

Max Range: 1.9750. Min Range: -1.9750

Max Act: 1.3871. Min Act: -0.0000

Data Index: 174051 (C4 (Web Text))

Max Activating Token Index: 615

Text #9

Max Range: 1.9750. Min Range: -1.9750

Max Act: 1.2609. Min Act: -0.0000

Data Index: 233379 (C4 (Web Text))

Max Activating Token Index: 979

Text #10

Max Range: 1.9750. Min Range: -1.9750

Max Act: 1.3379. Min Act: -0.0000

Data Index: 372457 (C4 (Web Text))

Max Activating Token Index: 421

Text #11

Max Range: 1.9750. Min Range: -1.9750

Max Act: 1.2414. Min Act: -0.0000

Data Index: 398394 (C4 (Web Text))

Max Activating Token Index: 115

Text #12

Max Range: 1.9750. Min Range: -1.9750

Max Act: 1.2858. Min Act: -0.0000

Data Index: 999142 (C4 (Web Text))

Max Activating Token Index: 221

Text #13

Max Range: 1.9750. Min Range: -1.9750

Max Act: 1.1258. Min Act: -0.0000

Data Index: 450772 (C4 (Web Text))

Max Activating Token Index: 411

Text #14

Max Range: 1.9750. Min Range: -1.9750

Max Act: 1.2032. Min Act: -0.0000

Data Index: 274813 (C4 (Web Text))

Max Activating Token Index: 721

Text #15

Max Range: 1.9750. Min Range: -1.9750

Max Act: 1.1991. Min Act: -0.0000

Data Index: 1313275 (C4 (Web Text))

Max Activating Token Index: 425

Text #16

Max Range: 1.9750. Min Range: -1.9750

Max Act: 1.1833. Min Act: -0.0000

Data Index: 1099206 (C4 (Web Text))

Max Activating Token Index: 988

Text #17

Max Range: 1.9750. Min Range: -1.9750

Max Act: 1.1149. Min Act: -0.0000

Data Index: 1172852 (C4 (Web Text))

Max Activating Token Index: 524

Text #18

Max Range: 1.9750. Min Range: -1.9750

Max Act: 1.1770. Min Act: -0.0000

Data Index: 478306 (C4 (Web Text))

Max Activating Token Index: 815

Text #19

Max Range: 1.9750. Min Range: -1.9750

Max Act: 1.1088. Min Act: -0.0000

Data Index: 1225572 (C4 (Web Text))

Max Activating Token Index: 254