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

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

Neuron 4676 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4716. Min Range: -3.4716

Max Act: 3.4716. Min Act: -0.0000

Data Index: 1407398 (Python Code)

Max Activating Token Index: 72

Text #1

Max Range: 3.4716. Min Range: -3.4716

Max Act: 3.1837. Min Act: -0.0000

Data Index: 1648487 (Python Code)

Max Activating Token Index: 223

Text #2

Max Range: 3.4716. Min Range: -3.4716

Max Act: 2.8088. Min Act: -0.0000

Data Index: 794552 (C4 (Web Text))

Max Activating Token Index: 656

Text #3

Max Range: 3.4716. Min Range: -3.4716

Max Act: 3.1692. Min Act: -0.0000

Data Index: 179966 (C4 (Web Text))

Max Activating Token Index: 697

Text #4

Max Range: 3.4716. Min Range: -3.4716

Max Act: 2.6945. Min Act: -0.0000

Data Index: 1033305 (C4 (Web Text))

Max Activating Token Index: 245

Text #5

Max Range: 3.4716. Min Range: -3.4716

Max Act: 3.0696. Min Act: -0.0000

Data Index: 770964 (C4 (Web Text))

Max Activating Token Index: 1012

Text #6

Max Range: 3.4716. Min Range: -3.4716

Max Act: 2.7384. Min Act: -0.0000

Data Index: 383013 (C4 (Web Text))

Max Activating Token Index: 584

Text #7

Max Range: 3.4716. Min Range: -3.4716

Max Act: 2.5548. Min Act: -0.0000

Data Index: 319774 (C4 (Web Text))

Max Activating Token Index: 287

Text #8

Max Range: 3.4716. Min Range: -3.4716

Max Act: 2.3988. Min Act: -0.0000

Data Index: 1371138 (Python Code)

Max Activating Token Index: 83

Text #9

Max Range: 3.4716. Min Range: -3.4716

Max Act: 2.4285. Min Act: -0.0000

Data Index: 1212127 (C4 (Web Text))

Max Activating Token Index: 268

Text #10

Max Range: 3.4716. Min Range: -3.4716

Max Act: 2.3207. Min Act: -0.0000

Data Index: 1495654 (Python Code)

Max Activating Token Index: 990

Text #11

Max Range: 3.4716. Min Range: -3.4716

Max Act: 2.1817. Min Act: -0.0000

Data Index: 480852 (C4 (Web Text))

Max Activating Token Index: 401

Text #12

Max Range: 3.4716. Min Range: -3.4716

Max Act: 2.2786. Min Act: -0.0000

Data Index: 970064 (C4 (Web Text))

Max Activating Token Index: 751

Text #13

Max Range: 3.4716. Min Range: -3.4716

Max Act: 2.3770. Min Act: -0.0000

Data Index: 523511 (C4 (Web Text))

Max Activating Token Index: 930

Text #14

Max Range: 3.4716. Min Range: -3.4716

Max Act: 2.2998. Min Act: -0.0000

Data Index: 1366595 (Python Code)

Max Activating Token Index: 207

Text #15

Max Range: 3.4716. Min Range: -3.4716

Max Act: 2.3804. Min Act: -0.0000

Data Index: 1385221 (Python Code)

Max Activating Token Index: 318

Text #16

Max Range: 3.4716. Min Range: -3.4716

Max Act: 2.2751. Min Act: -0.0000

Data Index: 1597603 (Python Code)

Max Activating Token Index: 721

Text #17

Max Range: 3.4716. Min Range: -3.4716

Max Act: 2.2698. Min Act: -0.0000

Data Index: 1619063 (Python Code)

Max Activating Token Index: 44

Text #18

Max Range: 3.4716. Min Range: -3.4716

Max Act: 2.1049. Min Act: -0.0000

Data Index: 918207 (C4 (Web Text))

Max Activating Token Index: 456

Text #19

Max Range: 3.4716. Min Range: -3.4716

Max Act: 2.0701. Min Act: -0.0000

Data Index: 309475 (C4 (Web Text))

Max Activating Token Index: 299