Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2546 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6382. Min Range: -0.6382

Max Act: 0.6382. Min Act: -0.0001

Data Index: 504141 (C4 (Web Text))

Max Activating Token Index: 86

Text #1

Max Range: 0.6382. Min Range: -0.6382

Max Act: 0.6014. Min Act: -0.0001

Data Index: 368338 (C4 (Web Text))

Max Activating Token Index: 108

Text #2

Max Range: 0.6382. Min Range: -0.6382

Max Act: 0.5524. Min Act: -0.0001

Data Index: 297648 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 0.6382. Min Range: -0.6382

Max Act: 0.5635. Min Act: -0.0001

Data Index: 778840 (C4 (Web Text))

Max Activating Token Index: 543

Text #4

Max Range: 0.6382. Min Range: -0.6382

Max Act: 0.5505. Min Act: -0.0001

Data Index: 361224 (C4 (Web Text))

Max Activating Token Index: 116

Text #5

Max Range: 0.6382. Min Range: -0.6382

Max Act: 0.5615. Min Act: -0.0001

Data Index: 33608 (C4 (Web Text))

Max Activating Token Index: 487

Text #6

Max Range: 0.6382. Min Range: -0.6382

Max Act: 0.5378. Min Act: -0.0001

Data Index: 260168 (C4 (Web Text))

Max Activating Token Index: 1005

Text #7

Max Range: 0.6382. Min Range: -0.6382

Max Act: 0.5468. Min Act: -0.0001

Data Index: 612084 (C4 (Web Text))

Max Activating Token Index: 626

Text #8

Max Range: 0.6382. Min Range: -0.6382

Max Act: 0.5072. Min Act: -0.0001

Data Index: 411784 (C4 (Web Text))

Max Activating Token Index: 419

Text #9

Max Range: 0.6382. Min Range: -0.6382

Max Act: 0.5242. Min Act: -0.0001

Data Index: 1045392 (C4 (Web Text))

Max Activating Token Index: 92

Text #10

Max Range: 0.6382. Min Range: -0.6382

Max Act: 0.4765. Min Act: -0.0001

Data Index: 1144848 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 0.6382. Min Range: -0.6382

Max Act: 0.4817. Min Act: -0.0001

Data Index: 886226 (C4 (Web Text))

Max Activating Token Index: 754

Text #12

Max Range: 0.6382. Min Range: -0.6382

Max Act: 0.4915. Min Act: -0.0001

Data Index: 593113 (C4 (Web Text))

Max Activating Token Index: 804

Text #13

Max Range: 0.6382. Min Range: -0.6382

Max Act: 0.4766. Min Act: -0.0001

Data Index: 404623 (C4 (Web Text))

Max Activating Token Index: 770

Text #14

Max Range: 0.6382. Min Range: -0.6382

Max Act: 0.4872. Min Act: -0.0001

Data Index: 553369 (C4 (Web Text))

Max Activating Token Index: 511

Text #15

Max Range: 0.6382. Min Range: -0.6382

Max Act: 0.4975. Min Act: -0.0001

Data Index: 977164 (C4 (Web Text))

Max Activating Token Index: 267

Text #16

Max Range: 0.6382. Min Range: -0.6382

Max Act: 0.4864. Min Act: -0.0001

Data Index: 1151648 (C4 (Web Text))

Max Activating Token Index: 671

Text #17

Max Range: 0.6382. Min Range: -0.6382

Max Act: 0.4792. Min Act: -0.0001

Data Index: 466660 (C4 (Web Text))

Max Activating Token Index: 719

Text #18

Max Range: 0.6382. Min Range: -0.6382

Max Act: 0.4786. Min Act: -0.0001

Data Index: 792419 (C4 (Web Text))

Max Activating Token Index: 751

Text #19

Max Range: 0.6382. Min Range: -0.6382

Max Act: 0.4756. Min Act: -0.0001

Data Index: 1255526 (C4 (Web Text))

Max Activating Token Index: 826