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

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

Neuron 3530 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: 0.0615. Min Range: -0.0615

Max Act: 0.0615. Min Act: -0.0003

Data Index: 544463 (C4 (Web Text))

Max Activating Token Index: 607

Text #1

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0595. Min Act: -0.0002

Data Index: 905764 (C4 (Web Text))

Max Activating Token Index: 144

Text #2

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0573. Min Act: -0.0003

Data Index: 1145512 (C4 (Web Text))

Max Activating Token Index: 238

Text #3

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0540. Min Act: -0.0003

Data Index: 262078 (C4 (Web Text))

Max Activating Token Index: 832

Text #4

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0509. Min Act: -0.0002

Data Index: 1192633 (C4 (Web Text))

Max Activating Token Index: 358

Text #5

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0509. Min Act: -0.0002

Data Index: 577912 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0524. Min Act: -0.0003

Data Index: 736566 (C4 (Web Text))

Max Activating Token Index: 187

Text #7

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0525. Min Act: -0.0002

Data Index: 754816 (C4 (Web Text))

Max Activating Token Index: 360

Text #8

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0520. Min Act: -0.0002

Data Index: 1341948 (C4 (Web Text))

Max Activating Token Index: 401

Text #9

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0497. Min Act: -0.0003

Data Index: 494952 (C4 (Web Text))

Max Activating Token Index: 541

Text #10

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0502. Min Act: -0.0002

Data Index: 1314211 (C4 (Web Text))

Max Activating Token Index: 870

Text #11

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0513. Min Act: -0.0003

Data Index: 536883 (C4 (Web Text))

Max Activating Token Index: 98

Text #12

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0491. Min Act: -0.0003

Data Index: 330748 (C4 (Web Text))

Max Activating Token Index: 122

Text #13

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0466. Min Act: -0.0003

Data Index: 727203 (C4 (Web Text))

Max Activating Token Index: 347

Text #14

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0472. Min Act: -0.0002

Data Index: 96719 (C4 (Web Text))

Max Activating Token Index: 520

Text #15

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0471. Min Act: -0.0003

Data Index: 416512 (C4 (Web Text))

Max Activating Token Index: 663

Text #16

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0475. Min Act: -0.0002

Data Index: 415550 (C4 (Web Text))

Max Activating Token Index: 270

Text #17

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0454. Min Act: -0.0002

Data Index: 923042 (C4 (Web Text))

Max Activating Token Index: 348

Text #18

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0440. Min Act: -0.0002

Data Index: 1328711 (C4 (Web Text))

Max Activating Token Index: 503

Text #19

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0442. Min Act: -0.0002

Data Index: 1077557 (C4 (Web Text))

Max Activating Token Index: 547