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

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

Neuron 4094 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0528. Min Act: -0.0002

Data Index: 1067318 (C4 (Web Text))

Max Activating Token Index: 717

Text #1

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0451. Min Act: -0.0002

Data Index: 1176498 (C4 (Web Text))

Max Activating Token Index: 876

Text #2

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0457. Min Act: -0.0002

Data Index: 419120 (C4 (Web Text))

Max Activating Token Index: 374

Text #3

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0430. Min Act: -0.0002

Data Index: 477919 (C4 (Web Text))

Max Activating Token Index: 249

Text #4

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0492. Min Act: -0.0002

Data Index: 604020 (C4 (Web Text))

Max Activating Token Index: 552

Text #5

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0438. Min Act: -0.0002

Data Index: 889515 (C4 (Web Text))

Max Activating Token Index: 945

Text #6

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0452. Min Act: -0.0002

Data Index: 264522 (C4 (Web Text))

Max Activating Token Index: 483

Text #7

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0454. Min Act: -0.0002

Data Index: 710398 (C4 (Web Text))

Max Activating Token Index: 50

Text #8

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0390. Min Act: -0.0002

Data Index: 1260557 (C4 (Web Text))

Max Activating Token Index: 376

Text #9

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0415. Min Act: -0.0002

Data Index: 5586 (C4 (Web Text))

Max Activating Token Index: 211

Text #10

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0420. Min Act: -0.0002

Data Index: 734982 (C4 (Web Text))

Max Activating Token Index: 146

Text #11

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0431. Min Act: -0.0002

Data Index: 1335912 (C4 (Web Text))

Max Activating Token Index: 451

Text #12

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0404. Min Act: -0.0002

Data Index: 117588 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0408. Min Act: -0.0002

Data Index: 700160 (C4 (Web Text))

Max Activating Token Index: 123

Text #14

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0438. Min Act: -0.0002

Data Index: 552826 (C4 (Web Text))

Max Activating Token Index: 89

Text #15

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0401. Min Act: -0.0002

Data Index: 1328476 (C4 (Web Text))

Max Activating Token Index: 660

Text #16

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0388. Min Act: -0.0002

Data Index: 432896 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0390. Min Act: -0.0002

Data Index: 311004 (C4 (Web Text))

Max Activating Token Index: 9

Text #18

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0368. Min Act: -0.0002

Data Index: 1195344 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0409. Min Act: -0.0002

Data Index: 537827 (C4 (Web Text))

Max Activating Token Index: 327