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

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

Neuron 4772 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.8072. Min Act: -0.0000

Data Index: 116097 (C4 (Web Text))

Max Activating Token Index: 876

Text #1

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.7406. Min Act: -0.0001

Data Index: 824666 (C4 (Web Text))

Max Activating Token Index: 953

Text #2

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.7114. Min Act: -0.0001

Data Index: 50765 (C4 (Web Text))

Max Activating Token Index: 542

Text #3

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.5240. Min Act: -0.0000

Data Index: 232674 (C4 (Web Text))

Max Activating Token Index: 477

Text #4

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.5392. Min Act: -0.0001

Data Index: 79217 (C4 (Web Text))

Max Activating Token Index: 442

Text #5

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.5585. Min Act: -0.0000

Data Index: 1330909 (C4 (Web Text))

Max Activating Token Index: 445

Text #6

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.5868. Min Act: -0.0000

Data Index: 1223351 (C4 (Web Text))

Max Activating Token Index: 888

Text #7

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.4867. Min Act: -0.0000

Data Index: 159257 (C4 (Web Text))

Max Activating Token Index: 31

Text #8

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.4231. Min Act: -0.0000

Data Index: 839126 (C4 (Web Text))

Max Activating Token Index: 887

Text #9

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.4577. Min Act: -0.0000

Data Index: 1305258 (C4 (Web Text))

Max Activating Token Index: 580

Text #10

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.4535. Min Act: -0.0000

Data Index: 80920 (C4 (Web Text))

Max Activating Token Index: 742

Text #11

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.4669. Min Act: -0.0000

Data Index: 342668 (C4 (Web Text))

Max Activating Token Index: 491

Text #12

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.4856. Min Act: -0.0001

Data Index: 295416 (C4 (Web Text))

Max Activating Token Index: 562

Text #13

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.4461. Min Act: -0.0000

Data Index: 517503 (C4 (Web Text))

Max Activating Token Index: 469

Text #14

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.4477. Min Act: -0.0000

Data Index: 1144818 (C4 (Web Text))

Max Activating Token Index: 453

Text #15

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.4582. Min Act: -0.0000

Data Index: 53591 (C4 (Web Text))

Max Activating Token Index: 108

Text #16

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.4752. Min Act: -0.0000

Data Index: 1232746 (C4 (Web Text))

Max Activating Token Index: 972

Text #17

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.4431. Min Act: -0.0000

Data Index: 1224236 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.4812. Min Act: -0.0000

Data Index: 803472 (C4 (Web Text))

Max Activating Token Index: 900

Text #19

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.3558. Min Act: -0.0000

Data Index: 1025260 (C4 (Web Text))

Max Activating Token Index: 857