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

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

Neuron 3209 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: 0.7604. Min Range: -0.7604

Max Act: 0.7222. Min Act: -0.0000

Data Index: 507070 (C4 (Web Text))

Max Activating Token Index: 517

Text #1

Max Range: 0.7604. Min Range: -0.7604

Max Act: 0.6717. Min Act: -0.0000

Data Index: 1129277 (C4 (Web Text))

Max Activating Token Index: 211

Text #2

Max Range: 0.7604. Min Range: -0.7604

Max Act: 0.7604. Min Act: -0.0000

Data Index: 649193 (C4 (Web Text))

Max Activating Token Index: 706

Text #3

Max Range: 0.7604. Min Range: -0.7604

Max Act: 0.6884. Min Act: -0.0000

Data Index: 446518 (C4 (Web Text))

Max Activating Token Index: 444

Text #4

Max Range: 0.7604. Min Range: -0.7604

Max Act: 0.7283. Min Act: -0.0000

Data Index: 611464 (C4 (Web Text))

Max Activating Token Index: 860

Text #5

Max Range: 0.7604. Min Range: -0.7604

Max Act: 0.7452. Min Act: -0.0000

Data Index: 1229595 (C4 (Web Text))

Max Activating Token Index: 874

Text #6

Max Range: 0.7604. Min Range: -0.7604

Max Act: 0.6663. Min Act: -0.0000

Data Index: 365105 (C4 (Web Text))

Max Activating Token Index: 283

Text #7

Max Range: 0.7604. Min Range: -0.7604

Max Act: 0.6960. Min Act: -0.0000

Data Index: 100695 (C4 (Web Text))

Max Activating Token Index: 473

Text #8

Max Range: 0.7604. Min Range: -0.7604

Max Act: 0.6411. Min Act: -0.0000

Data Index: 1353350 (C4 (Web Text))

Max Activating Token Index: 568

Text #9

Max Range: 0.7604. Min Range: -0.7604

Max Act: 0.6409. Min Act: -0.0000

Data Index: 662469 (C4 (Web Text))

Max Activating Token Index: 142

Text #10

Max Range: 0.7604. Min Range: -0.7604

Max Act: 0.6416. Min Act: -0.0000

Data Index: 1169079 (C4 (Web Text))

Max Activating Token Index: 74

Text #11

Max Range: 0.7604. Min Range: -0.7604

Max Act: 0.6167. Min Act: -0.0000

Data Index: 330818 (C4 (Web Text))

Max Activating Token Index: 339

Text #12

Max Range: 0.7604. Min Range: -0.7604

Max Act: 0.6180. Min Act: -0.0000

Data Index: 1104098 (C4 (Web Text))

Max Activating Token Index: 695

Text #13

Max Range: 0.7604. Min Range: -0.7604

Max Act: 0.5895. Min Act: -0.0000

Data Index: 447031 (C4 (Web Text))

Max Activating Token Index: 102

Text #14

Max Range: 0.7604. Min Range: -0.7604

Max Act: 0.6046. Min Act: -0.0000

Data Index: 1207231 (C4 (Web Text))

Max Activating Token Index: 961

Text #15

Max Range: 0.7604. Min Range: -0.7604

Max Act: 0.6225. Min Act: -0.0000

Data Index: 1154677 (C4 (Web Text))

Max Activating Token Index: 386

Text #16

Max Range: 0.7604. Min Range: -0.7604

Max Act: 0.5873. Min Act: -0.0000

Data Index: 1290849 (C4 (Web Text))

Max Activating Token Index: 331

Text #17

Max Range: 0.7604. Min Range: -0.7604

Max Act: 0.6167. Min Act: -0.0000

Data Index: 1233345 (C4 (Web Text))

Max Activating Token Index: 983

Text #18

Max Range: 0.7604. Min Range: -0.7604

Max Act: 0.6356. Min Act: -0.0000

Data Index: 1082188 (C4 (Web Text))

Max Activating Token Index: 1013

Text #19

Max Range: 0.7604. Min Range: -0.7604

Max Act: 0.5797. Min Act: -0.0000

Data Index: 753139 (C4 (Web Text))

Max Activating Token Index: 117