Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1003 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0604. Min Act: -0.0003

Data Index: 1339005 (C4 (Web Text))

Max Activating Token Index: 714

Text #1

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0598. Min Act: -0.0003

Data Index: 790106 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0560. Min Act: -0.0003

Data Index: 785593 (C4 (Web Text))

Max Activating Token Index: 968

Text #3

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0489. Min Act: -0.0004

Data Index: 822647 (C4 (Web Text))

Max Activating Token Index: 174

Text #4

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0508. Min Act: -0.0004

Data Index: 221906 (C4 (Web Text))

Max Activating Token Index: 12

Text #5

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0476. Min Act: -0.0004

Data Index: 590327 (C4 (Web Text))

Max Activating Token Index: 618

Text #6

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0488. Min Act: -0.0003

Data Index: 1233062 (C4 (Web Text))

Max Activating Token Index: 19

Text #7

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0476. Min Act: -0.0003

Data Index: 194759 (C4 (Web Text))

Max Activating Token Index: 824

Text #8

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0490. Min Act: -0.0003

Data Index: 1173188 (C4 (Web Text))

Max Activating Token Index: 371

Text #9

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0486. Min Act: -0.0003

Data Index: 1250869 (C4 (Web Text))

Max Activating Token Index: 713

Text #10

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0467. Min Act: -0.0003

Data Index: 829958 (C4 (Web Text))

Max Activating Token Index: 654

Text #11

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0475. Min Act: -0.0003

Data Index: 1047234 (C4 (Web Text))

Max Activating Token Index: 340

Text #12

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0461. Min Act: -0.0004

Data Index: 476743 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0454. Min Act: -0.0003

Data Index: 426525 (C4 (Web Text))

Max Activating Token Index: 717

Text #14

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0466. Min Act: -0.0003

Data Index: 684220 (C4 (Web Text))

Max Activating Token Index: 422

Text #15

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0456. Min Act: -0.0004

Data Index: 858309 (C4 (Web Text))

Max Activating Token Index: 836

Text #16

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0469. Min Act: -0.0003

Data Index: 303181 (C4 (Web Text))

Max Activating Token Index: 662

Text #17

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0458. Min Act: -0.0003

Data Index: 301121 (C4 (Web Text))

Max Activating Token Index: 127

Text #18

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0466. Min Act: -0.0003

Data Index: 1131154 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0449. Min Act: -0.0004

Data Index: 598024 (C4 (Web Text))

Max Activating Token Index: 711