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

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

Neuron 3471 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: 0.1132. Min Range: -0.1132

Max Act: 0.1072. Min Act: -0.0000

Data Index: 991253 (C4 (Web Text))

Max Activating Token Index: 751

Text #1

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.1132. Min Act: -0.0000

Data Index: 409644 (C4 (Web Text))

Max Activating Token Index: 711

Text #2

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.1094. Min Act: -0.0000

Data Index: 516598 (C4 (Web Text))

Max Activating Token Index: 234

Text #3

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.1060. Min Act: -0.0000

Data Index: 257045 (C4 (Web Text))

Max Activating Token Index: 38

Text #4

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0998. Min Act: -0.0000

Data Index: 887738 (C4 (Web Text))

Max Activating Token Index: 458

Text #5

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0889. Min Act: -0.0000

Data Index: 1304682 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0854. Min Act: -0.0000

Data Index: 283476 (C4 (Web Text))

Max Activating Token Index: 545

Text #7

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0863. Min Act: -0.0000

Data Index: 1231434 (C4 (Web Text))

Max Activating Token Index: 743

Text #8

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0788. Min Act: -0.0000

Data Index: 1135534 (C4 (Web Text))

Max Activating Token Index: 696

Text #9

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0787. Min Act: -0.0000

Data Index: 676780 (C4 (Web Text))

Max Activating Token Index: 865

Text #10

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0770. Min Act: -0.0000

Data Index: 263285 (C4 (Web Text))

Max Activating Token Index: 157

Text #11

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0788. Min Act: -0.0000

Data Index: 562435 (C4 (Web Text))

Max Activating Token Index: 512

Text #12

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0824. Min Act: -0.0000

Data Index: 1220179 (C4 (Web Text))

Max Activating Token Index: 749

Text #13

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0733. Min Act: -0.0000

Data Index: 1111057 (C4 (Web Text))

Max Activating Token Index: 251

Text #14

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0770. Min Act: -0.0000

Data Index: 804693 (C4 (Web Text))

Max Activating Token Index: 191

Text #15

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0747. Min Act: -0.0000

Data Index: 810068 (C4 (Web Text))

Max Activating Token Index: 485

Text #16

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0739. Min Act: -0.0000

Data Index: 328633 (C4 (Web Text))

Max Activating Token Index: 260

Text #17

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0736. Min Act: -0.0001

Data Index: 910096 (C4 (Web Text))

Max Activating Token Index: 549

Text #18

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0780. Min Act: -0.0000

Data Index: 866482 (C4 (Web Text))

Max Activating Token Index: 158

Text #19

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0674. Min Act: -0.0000

Data Index: 71501 (C4 (Web Text))

Max Activating Token Index: 49