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

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

Neuron 2705 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1672. Min Range: -4.1672

Max Act: 4.1672. Min Act: -0.0000

Data Index: 7006 (C4 (Web Text))

Max Activating Token Index: 560

Text #1

Max Range: 4.1672. Min Range: -4.1672

Max Act: 3.9639. Min Act: -0.0000

Data Index: 369964 (C4 (Web Text))

Max Activating Token Index: 315

Text #2

Max Range: 4.1672. Min Range: -4.1672

Max Act: 3.8976. Min Act: -0.0000

Data Index: 648872 (C4 (Web Text))

Max Activating Token Index: 588

Text #3

Max Range: 4.1672. Min Range: -4.1672

Max Act: 3.7145. Min Act: -0.0000

Data Index: 306708 (C4 (Web Text))

Max Activating Token Index: 910

Text #4

Max Range: 4.1672. Min Range: -4.1672

Max Act: 3.9896. Min Act: -0.0001

Data Index: 1200577 (C4 (Web Text))

Max Activating Token Index: 785

Text #5

Max Range: 4.1672. Min Range: -4.1672

Max Act: 3.5658. Min Act: -0.0000

Data Index: 1075446 (C4 (Web Text))

Max Activating Token Index: 741

Text #6

Max Range: 4.1672. Min Range: -4.1672

Max Act: 3.4413. Min Act: -0.0000

Data Index: 1041398 (C4 (Web Text))

Max Activating Token Index: 105

Text #7

Max Range: 4.1672. Min Range: -4.1672

Max Act: 3.4015. Min Act: -0.0000

Data Index: 1320451 (C4 (Web Text))

Max Activating Token Index: 721

Text #8

Max Range: 4.1672. Min Range: -4.1672

Max Act: 3.5867. Min Act: -0.0000

Data Index: 512861 (C4 (Web Text))

Max Activating Token Index: 773

Text #9

Max Range: 4.1672. Min Range: -4.1672

Max Act: 3.3588. Min Act: -0.0000

Data Index: 828826 (C4 (Web Text))

Max Activating Token Index: 188

Text #10

Max Range: 4.1672. Min Range: -4.1672

Max Act: 3.3131. Min Act: -0.0000

Data Index: 392564 (C4 (Web Text))

Max Activating Token Index: 524

Text #11

Max Range: 4.1672. Min Range: -4.1672

Max Act: 3.4393. Min Act: -0.0000

Data Index: 1146295 (C4 (Web Text))

Max Activating Token Index: 579

Text #12

Max Range: 4.1672. Min Range: -4.1672

Max Act: 3.4067. Min Act: -0.0000

Data Index: 24095 (C4 (Web Text))

Max Activating Token Index: 760

Text #13

Max Range: 4.1672. Min Range: -4.1672

Max Act: 3.0175. Min Act: -0.0000

Data Index: 112820 (C4 (Web Text))

Max Activating Token Index: 72

Text #14

Max Range: 4.1672. Min Range: -4.1672

Max Act: 3.5239. Min Act: -0.0000

Data Index: 146525 (C4 (Web Text))

Max Activating Token Index: 315

Text #15

Max Range: 4.1672. Min Range: -4.1672

Max Act: 3.4698. Min Act: -0.0000

Data Index: 1217682 (C4 (Web Text))

Max Activating Token Index: 903

Text #16

Max Range: 4.1672. Min Range: -4.1672

Max Act: 3.1268. Min Act: -0.0000

Data Index: 759846 (C4 (Web Text))

Max Activating Token Index: 508

Text #17

Max Range: 4.1672. Min Range: -4.1672

Max Act: 3.3683. Min Act: -0.0000

Data Index: 315749 (C4 (Web Text))

Max Activating Token Index: 785

Text #18

Max Range: 4.1672. Min Range: -4.1672

Max Act: 2.6750. Min Act: -0.0000

Data Index: 856433 (C4 (Web Text))

Max Activating Token Index: 284

Text #19

Max Range: 4.1672. Min Range: -4.1672

Max Act: 2.9225. Min Act: -0.0000

Data Index: 756324 (C4 (Web Text))

Max Activating Token Index: 501