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

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

Neuron 3659 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9863. Min Range: -2.9863

Max Act: 2.8492. Min Act: -0.0000

Data Index: 726762 (C4 (Web Text))

Max Activating Token Index: 722

Text #1

Max Range: 2.9863. Min Range: -2.9863

Max Act: 2.8518. Min Act: -0.0000

Data Index: 1063037 (C4 (Web Text))

Max Activating Token Index: 561

Text #2

Max Range: 2.9863. Min Range: -2.9863

Max Act: 2.9863. Min Act: -0.0000

Data Index: 1175177 (C4 (Web Text))

Max Activating Token Index: 770

Text #3

Max Range: 2.9863. Min Range: -2.9863

Max Act: 2.8195. Min Act: -0.0000

Data Index: 229903 (C4 (Web Text))

Max Activating Token Index: 389

Text #4

Max Range: 2.9863. Min Range: -2.9863

Max Act: 2.6940. Min Act: -0.0000

Data Index: 365446 (C4 (Web Text))

Max Activating Token Index: 151

Text #5

Max Range: 2.9863. Min Range: -2.9863

Max Act: 2.6032. Min Act: -0.0000

Data Index: 1233330 (C4 (Web Text))

Max Activating Token Index: 874

Text #6

Max Range: 2.9863. Min Range: -2.9863

Max Act: 2.5039. Min Act: -0.0000

Data Index: 7115 (C4 (Web Text))

Max Activating Token Index: 115

Text #7

Max Range: 2.9863. Min Range: -2.9863

Max Act: 2.2990. Min Act: -0.0000

Data Index: 249214 (C4 (Web Text))

Max Activating Token Index: 572

Text #8

Max Range: 2.9863. Min Range: -2.9863

Max Act: 2.2997. Min Act: -0.0000

Data Index: 224196 (C4 (Web Text))

Max Activating Token Index: 169

Text #9

Max Range: 2.9863. Min Range: -2.9863

Max Act: 2.2984. Min Act: -0.0000

Data Index: 1064087 (C4 (Web Text))

Max Activating Token Index: 403

Text #10

Max Range: 2.9863. Min Range: -2.9863

Max Act: 2.1406. Min Act: -0.0000

Data Index: 911827 (C4 (Web Text))

Max Activating Token Index: 692

Text #11

Max Range: 2.9863. Min Range: -2.9863

Max Act: 2.2418. Min Act: -0.0000

Data Index: 794721 (C4 (Web Text))

Max Activating Token Index: 525

Text #12

Max Range: 2.9863. Min Range: -2.9863

Max Act: 2.3467. Min Act: -0.0000

Data Index: 1165195 (C4 (Web Text))

Max Activating Token Index: 664

Text #13

Max Range: 2.9863. Min Range: -2.9863

Max Act: 2.3262. Min Act: -0.0000

Data Index: 148817 (C4 (Web Text))

Max Activating Token Index: 281

Text #14

Max Range: 2.9863. Min Range: -2.9863

Max Act: 2.2088. Min Act: -0.0000

Data Index: 917965 (C4 (Web Text))

Max Activating Token Index: 154

Text #15

Max Range: 2.9863. Min Range: -2.9863

Max Act: 2.2117. Min Act: -0.0000

Data Index: 1038613 (C4 (Web Text))

Max Activating Token Index: 338

Text #16

Max Range: 2.9863. Min Range: -2.9863

Max Act: 2.1838. Min Act: -0.0000

Data Index: 393484 (C4 (Web Text))

Max Activating Token Index: 511

Text #17

Max Range: 2.9863. Min Range: -2.9863

Max Act: 2.0610. Min Act: -0.0000

Data Index: 713761 (C4 (Web Text))

Max Activating Token Index: 155

Text #18

Max Range: 2.9863. Min Range: -2.9863

Max Act: 1.9452. Min Act: -0.0000

Data Index: 274626 (C4 (Web Text))

Max Activating Token Index: 516

Text #19

Max Range: 2.9863. Min Range: -2.9863

Max Act: 2.1518. Min Act: -0.0000

Data Index: 1268786 (C4 (Web Text))

Max Activating Token Index: 427