Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2347 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0711. Min Act: -0.0001

Data Index: 867587 (C4 (Web Text))

Max Activating Token Index: 494

Text #1

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0899. Min Act: -0.0001

Data Index: 1298599 (C4 (Web Text))

Max Activating Token Index: 676

Text #2

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0738. Min Act: -0.0001

Data Index: 1139531 (C4 (Web Text))

Max Activating Token Index: 429

Text #3

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0783. Min Act: -0.0001

Data Index: 438985 (C4 (Web Text))

Max Activating Token Index: 875

Text #4

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0786. Min Act: -0.0001

Data Index: 145468 (C4 (Web Text))

Max Activating Token Index: 655

Text #5

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0724. Min Act: -0.0001

Data Index: 839025 (C4 (Web Text))

Max Activating Token Index: 874

Text #6

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0694. Min Act: -0.0001

Data Index: 455124 (C4 (Web Text))

Max Activating Token Index: 951

Text #7

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0641. Min Act: -0.0001

Data Index: 727004 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0577. Min Act: -0.0001

Data Index: 1384281 (Python Code)

Max Activating Token Index: 666

Text #9

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0725. Min Act: -0.0001

Data Index: 1220234 (C4 (Web Text))

Max Activating Token Index: 670

Text #10

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0635. Min Act: -0.0001

Data Index: 1447758 (Python Code)

Max Activating Token Index: 990

Text #11

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0675. Min Act: -0.0001

Data Index: 571497 (C4 (Web Text))

Max Activating Token Index: 1003

Text #12

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0703. Min Act: -0.0001

Data Index: 89478 (C4 (Web Text))

Max Activating Token Index: 449

Text #13

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0700. Min Act: -0.0001

Data Index: 436993 (C4 (Web Text))

Max Activating Token Index: 973

Text #14

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0676. Min Act: -0.0001

Data Index: 1055179 (C4 (Web Text))

Max Activating Token Index: 935

Text #15

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0679. Min Act: -0.0001

Data Index: 164908 (C4 (Web Text))

Max Activating Token Index: 297

Text #16

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0672. Min Act: -0.0001

Data Index: 891245 (C4 (Web Text))

Max Activating Token Index: 341

Text #17

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0668. Min Act: -0.0001

Data Index: 566670 (C4 (Web Text))

Max Activating Token Index: 994

Text #18

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0650. Min Act: -0.0001

Data Index: 537873 (C4 (Web Text))

Max Activating Token Index: 784

Text #19

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0659. Min Act: -0.0001

Data Index: 293771 (C4 (Web Text))

Max Activating Token Index: 231