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

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

Neuron 1858 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0725. Min Act: -0.0006

Data Index: 589531 (C4 (Web Text))

Max Activating Token Index: 477

Text #1

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0705. Min Act: -0.0006

Data Index: 767110 (C4 (Web Text))

Max Activating Token Index: 357

Text #2

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0716. Min Act: -0.0006

Data Index: 125016 (C4 (Web Text))

Max Activating Token Index: 912

Text #3

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0674. Min Act: -0.0006

Data Index: 539644 (C4 (Web Text))

Max Activating Token Index: 852

Text #4

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0640. Min Act: -0.0006

Data Index: 903481 (C4 (Web Text))

Max Activating Token Index: 972

Text #5

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0625. Min Act: -0.0006

Data Index: 688947 (C4 (Web Text))

Max Activating Token Index: 786

Text #6

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0624. Min Act: -0.0006

Data Index: 971012 (C4 (Web Text))

Max Activating Token Index: 164

Text #7

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0624. Min Act: -0.0006

Data Index: 520967 (C4 (Web Text))

Max Activating Token Index: 1000

Text #8

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0606. Min Act: -0.0006

Data Index: 1359251 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0643. Min Act: -0.0006

Data Index: 1336845 (C4 (Web Text))

Max Activating Token Index: 853

Text #10

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0590. Min Act: -0.0006

Data Index: 1146103 (C4 (Web Text))

Max Activating Token Index: 391

Text #11

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0585. Min Act: -0.0006

Data Index: 769634 (C4 (Web Text))

Max Activating Token Index: 558

Text #12

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0567. Min Act: -0.0006

Data Index: 1110492 (C4 (Web Text))

Max Activating Token Index: 37

Text #13

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0600. Min Act: -0.0006

Data Index: 761057 (C4 (Web Text))

Max Activating Token Index: 593

Text #14

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0572. Min Act: -0.0006

Data Index: 181726 (C4 (Web Text))

Max Activating Token Index: 911

Text #15

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0593. Min Act: -0.0006

Data Index: 1285230 (C4 (Web Text))

Max Activating Token Index: 384

Text #16

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0557. Min Act: -0.0006

Data Index: 1123102 (C4 (Web Text))

Max Activating Token Index: 777

Text #17

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0579. Min Act: -0.0006

Data Index: 903872 (C4 (Web Text))

Max Activating Token Index: 551

Text #18

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0599. Min Act: -0.0006

Data Index: 310166 (C4 (Web Text))

Max Activating Token Index: 1011

Text #19

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0596. Min Act: -0.0006

Data Index: 1181473 (C4 (Web Text))

Max Activating Token Index: 308