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

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

Neuron 1414 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6692. Min Range: -1.6692

Max Act: 1.6692. Min Act: -0.0000

Data Index: 1421169 (Python Code)

Max Activating Token Index: 91

Text #1

Max Range: 1.6692. Min Range: -1.6692

Max Act: 1.4700. Min Act: -0.0000

Data Index: 61176 (C4 (Web Text))

Max Activating Token Index: 415

Text #2

Max Range: 1.6692. Min Range: -1.6692

Max Act: 1.2819. Min Act: -0.0000

Data Index: 1241139 (C4 (Web Text))

Max Activating Token Index: 374

Text #3

Max Range: 1.6692. Min Range: -1.6692

Max Act: 1.1056. Min Act: -0.0000

Data Index: 1584714 (Python Code)

Max Activating Token Index: 692

Text #4

Max Range: 1.6692. Min Range: -1.6692

Max Act: 1.0325. Min Act: -0.0000

Data Index: 1629088 (Python Code)

Max Activating Token Index: 607

Text #5

Max Range: 1.6692. Min Range: -1.6692

Max Act: 1.0765. Min Act: -0.0000

Data Index: 49669 (C4 (Web Text))

Max Activating Token Index: 231

Text #6

Max Range: 1.6692. Min Range: -1.6692

Max Act: 1.1112. Min Act: -0.0000

Data Index: 540718 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 1.6692. Min Range: -1.6692

Max Act: 1.1109. Min Act: -0.0000

Data Index: 256529 (C4 (Web Text))

Max Activating Token Index: 286

Text #8

Max Range: 1.6692. Min Range: -1.6692

Max Act: 1.0975. Min Act: -0.0000

Data Index: 1018288 (C4 (Web Text))

Max Activating Token Index: 180

Text #9

Max Range: 1.6692. Min Range: -1.6692

Max Act: 1.0546. Min Act: -0.0000

Data Index: 1010797 (C4 (Web Text))

Max Activating Token Index: 399

Text #10

Max Range: 1.6692. Min Range: -1.6692

Max Act: 0.9284. Min Act: -0.0000

Data Index: 1587467 (Python Code)

Max Activating Token Index: 673

Text #11

Max Range: 1.6692. Min Range: -1.6692

Max Act: 1.0573. Min Act: -0.0000

Data Index: 702786 (C4 (Web Text))

Max Activating Token Index: 485

Text #12

Max Range: 1.6692. Min Range: -1.6692

Max Act: 0.8457. Min Act: -0.0000

Data Index: 1554013 (Python Code)

Max Activating Token Index: 893

Text #13

Max Range: 1.6692. Min Range: -1.6692

Max Act: 1.0504. Min Act: -0.0000

Data Index: 591693 (C4 (Web Text))

Max Activating Token Index: 880

Text #14

Max Range: 1.6692. Min Range: -1.6692

Max Act: 1.0134. Min Act: -0.0000

Data Index: 54598 (C4 (Web Text))

Max Activating Token Index: 519

Text #15

Max Range: 1.6692. Min Range: -1.6692

Max Act: 1.0041. Min Act: -0.0000

Data Index: 664879 (C4 (Web Text))

Max Activating Token Index: 742

Text #16

Max Range: 1.6692. Min Range: -1.6692

Max Act: 0.9628. Min Act: -0.0000

Data Index: 1286341 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 1.6692. Min Range: -1.6692

Max Act: 0.9714. Min Act: -0.0000

Data Index: 726704 (C4 (Web Text))

Max Activating Token Index: 497

Text #18

Max Range: 1.6692. Min Range: -1.6692

Max Act: 0.7501. Min Act: -0.0000

Data Index: 32757 (C4 (Web Text))

Max Activating Token Index: 641

Text #19

Max Range: 1.6692. Min Range: -1.6692

Max Act: 0.9698. Min Act: -0.0000

Data Index: 1278645 (C4 (Web Text))

Max Activating Token Index: 893