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

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

Neuron 3408 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2875. Min Range: -1.2875

Max Act: 1.2844. Min Act: -0.0000

Data Index: 588602 (C4 (Web Text))

Max Activating Token Index: 300

Text #1

Max Range: 1.2875. Min Range: -1.2875

Max Act: 1.2875. Min Act: -0.0000

Data Index: 1514104 (Python Code)

Max Activating Token Index: 24

Text #2

Max Range: 1.2875. Min Range: -1.2875

Max Act: 1.2008. Min Act: -0.0000

Data Index: 84028 (C4 (Web Text))

Max Activating Token Index: 574

Text #3

Max Range: 1.2875. Min Range: -1.2875

Max Act: 1.1571. Min Act: -0.0000

Data Index: 1203491 (C4 (Web Text))

Max Activating Token Index: 342

Text #4

Max Range: 1.2875. Min Range: -1.2875

Max Act: 1.0229. Min Act: -0.0000

Data Index: 594616 (C4 (Web Text))

Max Activating Token Index: 450

Text #5

Max Range: 1.2875. Min Range: -1.2875

Max Act: 1.0546. Min Act: -0.0000

Data Index: 1216019 (C4 (Web Text))

Max Activating Token Index: 572

Text #6

Max Range: 1.2875. Min Range: -1.2875

Max Act: 1.0304. Min Act: 0.0000

Data Index: 1504891 (Python Code)

Max Activating Token Index: 122

Text #7

Max Range: 1.2875. Min Range: -1.2875

Max Act: 0.9525. Min Act: -0.0000

Data Index: 1240710 (C4 (Web Text))

Max Activating Token Index: 1006

Text #8

Max Range: 1.2875. Min Range: -1.2875

Max Act: 1.0516. Min Act: -0.0000

Data Index: 493344 (C4 (Web Text))

Max Activating Token Index: 294

Text #9

Max Range: 1.2875. Min Range: -1.2875

Max Act: 1.0468. Min Act: -0.0000

Data Index: 21026 (C4 (Web Text))

Max Activating Token Index: 249

Text #10

Max Range: 1.2875. Min Range: -1.2875

Max Act: 1.0630. Min Act: -0.0000

Data Index: 1138352 (C4 (Web Text))

Max Activating Token Index: 591

Text #11

Max Range: 1.2875. Min Range: -1.2875

Max Act: 0.9054. Min Act: -0.0000

Data Index: 1495980 (Python Code)

Max Activating Token Index: 231

Text #12

Max Range: 1.2875. Min Range: -1.2875

Max Act: 0.9635. Min Act: -0.0000

Data Index: 1433403 (Python Code)

Max Activating Token Index: 280

Text #13

Max Range: 1.2875. Min Range: -1.2875

Max Act: 0.9594. Min Act: -0.0000

Data Index: 1051007 (C4 (Web Text))

Max Activating Token Index: 246

Text #14

Max Range: 1.2875. Min Range: -1.2875

Max Act: 0.9556. Min Act: -0.0000

Data Index: 181158 (C4 (Web Text))

Max Activating Token Index: 243

Text #15

Max Range: 1.2875. Min Range: -1.2875

Max Act: 0.9398. Min Act: -0.0000

Data Index: 920375 (C4 (Web Text))

Max Activating Token Index: 840

Text #16

Max Range: 1.2875. Min Range: -1.2875

Max Act: 0.9908. Min Act: 0.0000

Data Index: 1382436 (Python Code)

Max Activating Token Index: 644

Text #17

Max Range: 1.2875. Min Range: -1.2875

Max Act: 0.9978. Min Act: -0.0000

Data Index: 1620174 (Python Code)

Max Activating Token Index: 407

Text #18

Max Range: 1.2875. Min Range: -1.2875

Max Act: 0.9219. Min Act: -0.0000

Data Index: 1092021 (C4 (Web Text))

Max Activating Token Index: 475

Text #19

Max Range: 1.2875. Min Range: -1.2875

Max Act: 0.8743. Min Act: -0.0000

Data Index: 397687 (C4 (Web Text))

Max Activating Token Index: 570