Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4302 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9784. Min Range: -0.9784

Max Act: 0.9784. Min Act: -0.0001

Data Index: 162561 (C4 (Web Text))

Max Activating Token Index: 183

Text #1

Max Range: 0.9784. Min Range: -0.9784

Max Act: 0.8719. Min Act: -0.0002

Data Index: 141541 (C4 (Web Text))

Max Activating Token Index: 914

Text #2

Max Range: 0.9784. Min Range: -0.9784

Max Act: 0.9667. Min Act: -0.0002

Data Index: 1070039 (C4 (Web Text))

Max Activating Token Index: 284

Text #3

Max Range: 0.9784. Min Range: -0.9784

Max Act: 0.8398. Min Act: -0.0002

Data Index: 1262112 (C4 (Web Text))

Max Activating Token Index: 502

Text #4

Max Range: 0.9784. Min Range: -0.9784

Max Act: 0.7871. Min Act: -0.0002

Data Index: 663041 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 0.9784. Min Range: -0.9784

Max Act: 0.7289. Min Act: -0.0002

Data Index: 616504 (C4 (Web Text))

Max Activating Token Index: 288

Text #6

Max Range: 0.9784. Min Range: -0.9784

Max Act: 0.7922. Min Act: -0.0002

Data Index: 841246 (C4 (Web Text))

Max Activating Token Index: 888

Text #7

Max Range: 0.9784. Min Range: -0.9784

Max Act: 0.7106. Min Act: -0.0002

Data Index: 171785 (C4 (Web Text))

Max Activating Token Index: 481

Text #8

Max Range: 0.9784. Min Range: -0.9784

Max Act: 0.7298. Min Act: -0.0002

Data Index: 619508 (C4 (Web Text))

Max Activating Token Index: 397

Text #9

Max Range: 0.9784. Min Range: -0.9784

Max Act: 0.7198. Min Act: -0.0002

Data Index: 163226 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 0.9784. Min Range: -0.9784

Max Act: 0.7142. Min Act: -0.0002

Data Index: 1237039 (C4 (Web Text))

Max Activating Token Index: 470

Text #11

Max Range: 0.9784. Min Range: -0.9784

Max Act: 0.7085. Min Act: -0.0002

Data Index: 54493 (C4 (Web Text))

Max Activating Token Index: 913

Text #12

Max Range: 0.9784. Min Range: -0.9784

Max Act: 0.6499. Min Act: -0.0002

Data Index: 24763 (C4 (Web Text))

Max Activating Token Index: 246

Text #13

Max Range: 0.9784. Min Range: -0.9784

Max Act: 0.6455. Min Act: -0.0002

Data Index: 226708 (C4 (Web Text))

Max Activating Token Index: 599

Text #14

Max Range: 0.9784. Min Range: -0.9784

Max Act: 0.6605. Min Act: -0.0002

Data Index: 1082832 (C4 (Web Text))

Max Activating Token Index: 85

Text #15

Max Range: 0.9784. Min Range: -0.9784

Max Act: 0.6607. Min Act: -0.0002

Data Index: 1165928 (C4 (Web Text))

Max Activating Token Index: 83

Text #16

Max Range: 0.9784. Min Range: -0.9784

Max Act: 0.6253. Min Act: -0.0002

Data Index: 578386 (C4 (Web Text))

Max Activating Token Index: 449

Text #17

Max Range: 0.9784. Min Range: -0.9784

Max Act: 0.6556. Min Act: -0.0002

Data Index: 217899 (C4 (Web Text))

Max Activating Token Index: 774

Text #18

Max Range: 0.9784. Min Range: -0.9784

Max Act: 0.5511. Min Act: -0.0002

Data Index: 982226 (C4 (Web Text))

Max Activating Token Index: 323

Text #19

Max Range: 0.9784. Min Range: -0.9784

Max Act: 0.6666. Min Act: -0.0002

Data Index: 737063 (C4 (Web Text))

Max Activating Token Index: 453