Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2486 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4765. Min Range: -0.4765

Max Act: 0.4765. Min Act: -0.0002

Data Index: 735607 (C4 (Web Text))

Max Activating Token Index: 623

Text #1

Max Range: 0.4765. Min Range: -0.4765

Max Act: 0.4436. Min Act: -0.0001

Data Index: 309617 (C4 (Web Text))

Max Activating Token Index: 402

Text #2

Max Range: 0.4765. Min Range: -0.4765

Max Act: 0.4308. Min Act: -0.0001

Data Index: 1399464 (Python Code)

Max Activating Token Index: 296

Text #3

Max Range: 0.4765. Min Range: -0.4765

Max Act: 0.4147. Min Act: -0.0001

Data Index: 409766 (C4 (Web Text))

Max Activating Token Index: 48

Text #4

Max Range: 0.4765. Min Range: -0.4765

Max Act: 0.3872. Min Act: -0.0001

Data Index: 726927 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 0.4765. Min Range: -0.4765

Max Act: 0.4118. Min Act: -0.0001

Data Index: 585073 (C4 (Web Text))

Max Activating Token Index: 529

Text #6

Max Range: 0.4765. Min Range: -0.4765

Max Act: 0.3943. Min Act: -0.0001

Data Index: 437126 (C4 (Web Text))

Max Activating Token Index: 546

Text #7

Max Range: 0.4765. Min Range: -0.4765

Max Act: 0.3917. Min Act: -0.0002

Data Index: 368182 (C4 (Web Text))

Max Activating Token Index: 927

Text #8

Max Range: 0.4765. Min Range: -0.4765

Max Act: 0.4090. Min Act: -0.0002

Data Index: 870840 (C4 (Web Text))

Max Activating Token Index: 182

Text #9

Max Range: 0.4765. Min Range: -0.4765

Max Act: 0.4454. Min Act: -0.0001

Data Index: 1279915 (C4 (Web Text))

Max Activating Token Index: 796

Text #10

Max Range: 0.4765. Min Range: -0.4765

Max Act: 0.4121. Min Act: -0.0002

Data Index: 1018919 (C4 (Web Text))

Max Activating Token Index: 862

Text #11

Max Range: 0.4765. Min Range: -0.4765

Max Act: 0.3875. Min Act: -0.0001

Data Index: 552310 (C4 (Web Text))

Max Activating Token Index: 135

Text #12

Max Range: 0.4765. Min Range: -0.4765

Max Act: 0.3980. Min Act: -0.0002

Data Index: 354082 (C4 (Web Text))

Max Activating Token Index: 229

Text #13

Max Range: 0.4765. Min Range: -0.4765

Max Act: 0.3920. Min Act: -0.0001

Data Index: 390679 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 0.4765. Min Range: -0.4765

Max Act: 0.3955. Min Act: -0.0001

Data Index: 1272654 (C4 (Web Text))

Max Activating Token Index: 392

Text #15

Max Range: 0.4765. Min Range: -0.4765

Max Act: 0.3780. Min Act: -0.0001

Data Index: 868989 (C4 (Web Text))

Max Activating Token Index: 448

Text #16

Max Range: 0.4765. Min Range: -0.4765

Max Act: 0.3820. Min Act: -0.0001

Data Index: 438850 (C4 (Web Text))

Max Activating Token Index: 22

Text #17

Max Range: 0.4765. Min Range: -0.4765

Max Act: 0.3782. Min Act: -0.0002

Data Index: 254682 (C4 (Web Text))

Max Activating Token Index: 408

Text #18

Max Range: 0.4765. Min Range: -0.4765

Max Act: 0.3628. Min Act: -0.0002

Data Index: 211316 (C4 (Web Text))

Max Activating Token Index: 106

Text #19

Max Range: 0.4765. Min Range: -0.4765

Max Act: 0.3739. Min Act: -0.0001

Data Index: 623950 (C4 (Web Text))

Max Activating Token Index: 31