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

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

Neuron 325 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: 0.0839. Min Range: -0.0839

Max Act: 0.0839. Min Act: -0.0002

Data Index: 987405 (C4 (Web Text))

Max Activating Token Index: 281

Text #1

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0773. Min Act: -0.0002

Data Index: 937584 (C4 (Web Text))

Max Activating Token Index: 504

Text #2

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0765. Min Act: -0.0002

Data Index: 445136 (C4 (Web Text))

Max Activating Token Index: 54

Text #3

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0743. Min Act: -0.0002

Data Index: 531025 (C4 (Web Text))

Max Activating Token Index: 446

Text #4

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0737. Min Act: -0.0002

Data Index: 1266584 (C4 (Web Text))

Max Activating Token Index: 158

Text #5

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0663. Min Act: -0.0002

Data Index: 333032 (C4 (Web Text))

Max Activating Token Index: 73

Text #6

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0672. Min Act: -0.0002

Data Index: 149130 (C4 (Web Text))

Max Activating Token Index: 206

Text #7

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0683. Min Act: -0.0002

Data Index: 153723 (C4 (Web Text))

Max Activating Token Index: 113

Text #8

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0705. Min Act: -0.0002

Data Index: 516789 (C4 (Web Text))

Max Activating Token Index: 179

Text #9

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0655. Min Act: -0.0002

Data Index: 1348554 (C4 (Web Text))

Max Activating Token Index: 173

Text #10

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0663. Min Act: -0.0002

Data Index: 171842 (C4 (Web Text))

Max Activating Token Index: 144

Text #11

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0652. Min Act: -0.0002

Data Index: 801962 (C4 (Web Text))

Max Activating Token Index: 395

Text #12

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0648. Min Act: -0.0002

Data Index: 913554 (C4 (Web Text))

Max Activating Token Index: 112

Text #13

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0645. Min Act: -0.0002

Data Index: 1220049 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0618. Min Act: -0.0002

Data Index: 914536 (C4 (Web Text))

Max Activating Token Index: 209

Text #15

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0631. Min Act: -0.0002

Data Index: 1096271 (C4 (Web Text))

Max Activating Token Index: 232

Text #16

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0597. Min Act: -0.0002

Data Index: 1284610 (C4 (Web Text))

Max Activating Token Index: 123

Text #17

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0643. Min Act: -0.0002

Data Index: 267967 (C4 (Web Text))

Max Activating Token Index: 229

Text #18

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0615. Min Act: -0.0002

Data Index: 779607 (C4 (Web Text))

Max Activating Token Index: 322

Text #19

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0616. Min Act: -0.0002

Data Index: 1013804 (C4 (Web Text))

Max Activating Token Index: 663