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

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

Neuron 4679 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0892. Min Act: -0.0003

Data Index: 74819 (C4 (Web Text))

Max Activating Token Index: 684

Text #1

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0724. Min Act: -0.0003

Data Index: 123123 (C4 (Web Text))

Max Activating Token Index: 517

Text #2

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0664. Min Act: -0.0003

Data Index: 724800 (C4 (Web Text))

Max Activating Token Index: 152

Text #3

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0638. Min Act: -0.0003

Data Index: 1333157 (C4 (Web Text))

Max Activating Token Index: 969

Text #4

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0544. Min Act: -0.0003

Data Index: 286453 (C4 (Web Text))

Max Activating Token Index: 865

Text #5

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0542. Min Act: -0.0003

Data Index: 167446 (C4 (Web Text))

Max Activating Token Index: 494

Text #6

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0511. Min Act: -0.0003

Data Index: 501667 (C4 (Web Text))

Max Activating Token Index: 869

Text #7

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0526. Min Act: -0.0003

Data Index: 1334442 (C4 (Web Text))

Max Activating Token Index: 1004

Text #8

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0520. Min Act: -0.0003

Data Index: 1110881 (C4 (Web Text))

Max Activating Token Index: 963

Text #9

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0518. Min Act: -0.0003

Data Index: 937676 (C4 (Web Text))

Max Activating Token Index: 507

Text #10

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0513. Min Act: -0.0003

Data Index: 945594 (C4 (Web Text))

Max Activating Token Index: 601

Text #11

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0489. Min Act: -0.0003

Data Index: 1336747 (C4 (Web Text))

Max Activating Token Index: 635

Text #12

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0501. Min Act: -0.0003

Data Index: 591605 (C4 (Web Text))

Max Activating Token Index: 399

Text #13

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0487. Min Act: -0.0003

Data Index: 1216658 (C4 (Web Text))

Max Activating Token Index: 40

Text #14

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0489. Min Act: -0.0003

Data Index: 424816 (C4 (Web Text))

Max Activating Token Index: 712

Text #15

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0465. Min Act: -0.0003

Data Index: 780414 (C4 (Web Text))

Max Activating Token Index: 948

Text #16

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0465. Min Act: -0.0003

Data Index: 217492 (C4 (Web Text))

Max Activating Token Index: 365

Text #17

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0471. Min Act: -0.0003

Data Index: 1044716 (C4 (Web Text))

Max Activating Token Index: 158

Text #18

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0473. Min Act: -0.0003

Data Index: 1162630 (C4 (Web Text))

Max Activating Token Index: 184

Text #19

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0469. Min Act: -0.0003

Data Index: 405019 (C4 (Web Text))

Max Activating Token Index: 221