Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3809 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.5919. Min Act: -0.0000

Data Index: 64101 (C4 (Web Text))

Max Activating Token Index: 574

Text #1

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.3333. Min Act: -0.0000

Data Index: 907909 (C4 (Web Text))

Max Activating Token Index: 692

Text #2

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.2487. Min Act: -0.0000

Data Index: 1078152 (C4 (Web Text))

Max Activating Token Index: 843

Text #3

Max Range: 1.5919. Min Range: -1.5919

Max Act: 0.9570. Min Act: -0.0000

Data Index: 407356 (C4 (Web Text))

Max Activating Token Index: 1003

Text #4

Max Range: 1.5919. Min Range: -1.5919

Max Act: 0.8585. Min Act: -0.0000

Data Index: 229573 (C4 (Web Text))

Max Activating Token Index: 807

Text #5

Max Range: 1.5919. Min Range: -1.5919

Max Act: 0.8860. Min Act: -0.0000

Data Index: 49638 (C4 (Web Text))

Max Activating Token Index: 278

Text #6

Max Range: 1.5919. Min Range: -1.5919

Max Act: 0.8265. Min Act: -0.0000

Data Index: 946537 (C4 (Web Text))

Max Activating Token Index: 581

Text #7

Max Range: 1.5919. Min Range: -1.5919

Max Act: 0.7785. Min Act: -0.0000

Data Index: 291194 (C4 (Web Text))

Max Activating Token Index: 52

Text #8

Max Range: 1.5919. Min Range: -1.5919

Max Act: 0.7658. Min Act: -0.0000

Data Index: 646122 (C4 (Web Text))

Max Activating Token Index: 164

Text #9

Max Range: 1.5919. Min Range: -1.5919

Max Act: 0.7826. Min Act: -0.0000

Data Index: 1166229 (C4 (Web Text))

Max Activating Token Index: 670

Text #10

Max Range: 1.5919. Min Range: -1.5919

Max Act: 0.7977. Min Act: -0.0000

Data Index: 63408 (C4 (Web Text))

Max Activating Token Index: 259

Text #11

Max Range: 1.5919. Min Range: -1.5919

Max Act: 0.7468. Min Act: -0.0000

Data Index: 707638 (C4 (Web Text))

Max Activating Token Index: 656

Text #12

Max Range: 1.5919. Min Range: -1.5919

Max Act: 0.7682. Min Act: -0.0000

Data Index: 25098 (C4 (Web Text))

Max Activating Token Index: 182

Text #13

Max Range: 1.5919. Min Range: -1.5919

Max Act: 0.7686. Min Act: -0.0000

Data Index: 250790 (C4 (Web Text))

Max Activating Token Index: 675

Text #14

Max Range: 1.5919. Min Range: -1.5919

Max Act: 0.7395. Min Act: -0.0000

Data Index: 1303601 (C4 (Web Text))

Max Activating Token Index: 757

Text #15

Max Range: 1.5919. Min Range: -1.5919

Max Act: 0.7335. Min Act: -0.0000

Data Index: 990165 (C4 (Web Text))

Max Activating Token Index: 595

Text #16

Max Range: 1.5919. Min Range: -1.5919

Max Act: 0.6569. Min Act: -0.0000

Data Index: 180953 (C4 (Web Text))

Max Activating Token Index: 262

Text #17

Max Range: 1.5919. Min Range: -1.5919

Max Act: 0.6963. Min Act: -0.0000

Data Index: 372076 (C4 (Web Text))

Max Activating Token Index: 862

Text #18

Max Range: 1.5919. Min Range: -1.5919

Max Act: 0.7184. Min Act: -0.0000

Data Index: 404100 (C4 (Web Text))

Max Activating Token Index: 579

Text #19

Max Range: 1.5919. Min Range: -1.5919

Max Act: 0.7403. Min Act: -0.0000

Data Index: 1119069 (C4 (Web Text))

Max Activating Token Index: 327