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

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

Neuron 3686 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: 0.2406. Min Range: -0.2406

Max Act: 0.2406. Min Act: -0.0002

Data Index: 219366 (C4 (Web Text))

Max Activating Token Index: 645

Text #1

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.2059. Min Act: -0.0002

Data Index: 3205 (C4 (Web Text))

Max Activating Token Index: 269

Text #2

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1978. Min Act: -0.0002

Data Index: 1018000 (C4 (Web Text))

Max Activating Token Index: 206

Text #3

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1930. Min Act: -0.0002

Data Index: 610174 (C4 (Web Text))

Max Activating Token Index: 864

Text #4

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.2023. Min Act: -0.0002

Data Index: 1158797 (C4 (Web Text))

Max Activating Token Index: 739

Text #5

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1873. Min Act: -0.0002

Data Index: 6420 (C4 (Web Text))

Max Activating Token Index: 144

Text #6

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1919. Min Act: -0.0002

Data Index: 458092 (C4 (Web Text))

Max Activating Token Index: 880

Text #7

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1904. Min Act: -0.0002

Data Index: 1359669 (C4 (Web Text))

Max Activating Token Index: 77

Text #8

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1832. Min Act: -0.0002

Data Index: 927144 (C4 (Web Text))

Max Activating Token Index: 236

Text #9

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1779. Min Act: -0.0002

Data Index: 773133 (C4 (Web Text))

Max Activating Token Index: 67

Text #10

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1776. Min Act: -0.0002

Data Index: 750994 (C4 (Web Text))

Max Activating Token Index: 525

Text #11

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1723. Min Act: -0.0002

Data Index: 495836 (C4 (Web Text))

Max Activating Token Index: 335

Text #12

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1740. Min Act: -0.0002

Data Index: 131319 (C4 (Web Text))

Max Activating Token Index: 210

Text #13

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1733. Min Act: -0.0002

Data Index: 1102643 (C4 (Web Text))

Max Activating Token Index: 763

Text #14

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1668. Min Act: -0.0002

Data Index: 341155 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1667. Min Act: -0.0002

Data Index: 542478 (C4 (Web Text))

Max Activating Token Index: 678

Text #16

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1567. Min Act: -0.0002

Data Index: 1088248 (C4 (Web Text))

Max Activating Token Index: 184

Text #17

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1694. Min Act: -0.0002

Data Index: 869769 (C4 (Web Text))

Max Activating Token Index: 492

Text #18

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1624. Min Act: -0.0002

Data Index: 1146319 (C4 (Web Text))

Max Activating Token Index: 547

Text #19

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1531. Min Act: -0.0002

Data Index: 590122 (C4 (Web Text))

Max Activating Token Index: 308