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

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

Neuron 4500 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: 0.0612. Min Range: -0.0612

Max Act: 0.0612. Min Act: -0.0002

Data Index: 1297964 (C4 (Web Text))

Max Activating Token Index: 186

Text #1

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0611. Min Act: -0.0003

Data Index: 892383 (C4 (Web Text))

Max Activating Token Index: 98

Text #2

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0562. Min Act: -0.0002

Data Index: 1236544 (C4 (Web Text))

Max Activating Token Index: 234

Text #3

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0553. Min Act: -0.0003

Data Index: 151153 (C4 (Web Text))

Max Activating Token Index: 116

Text #4

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0540. Min Act: -0.0002

Data Index: 287454 (C4 (Web Text))

Max Activating Token Index: 646

Text #5

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0540. Min Act: -0.0002

Data Index: 1354301 (C4 (Web Text))

Max Activating Token Index: 698

Text #6

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0530. Min Act: -0.0002

Data Index: 579886 (C4 (Web Text))

Max Activating Token Index: 439

Text #7

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0536. Min Act: -0.0002

Data Index: 183434 (C4 (Web Text))

Max Activating Token Index: 765

Text #8

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0506. Min Act: -0.0002

Data Index: 84078 (C4 (Web Text))

Max Activating Token Index: 158

Text #9

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0513. Min Act: -0.0002

Data Index: 594648 (C4 (Web Text))

Max Activating Token Index: 816

Text #10

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0481. Min Act: -0.0003

Data Index: 303995 (C4 (Web Text))

Max Activating Token Index: 604

Text #11

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0503. Min Act: -0.0002

Data Index: 140851 (C4 (Web Text))

Max Activating Token Index: 640

Text #12

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0504. Min Act: -0.0002

Data Index: 391785 (C4 (Web Text))

Max Activating Token Index: 252

Text #13

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0483. Min Act: -0.0002

Data Index: 849771 (C4 (Web Text))

Max Activating Token Index: 208

Text #14

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0491. Min Act: -0.0003

Data Index: 162471 (C4 (Web Text))

Max Activating Token Index: 373

Text #15

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0468. Min Act: -0.0003

Data Index: 237968 (C4 (Web Text))

Max Activating Token Index: 226

Text #16

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0479. Min Act: -0.0003

Data Index: 159816 (C4 (Web Text))

Max Activating Token Index: 86

Text #17

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0491. Min Act: -0.0002

Data Index: 717003 (C4 (Web Text))

Max Activating Token Index: 505

Text #18

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0491. Min Act: -0.0002

Data Index: 356248 (C4 (Web Text))

Max Activating Token Index: 968

Text #19

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0462. Min Act: -0.0002

Data Index: 528654 (C4 (Web Text))

Max Activating Token Index: 228