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

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

Neuron 5743 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5762. Min Range: -3.5762

Max Act: 3.5762. Min Act: -0.0000

Data Index: 1626433 (Python Code)

Max Activating Token Index: 1008

Text #1

Max Range: 3.5762. Min Range: -3.5762

Max Act: 2.6297. Min Act: -0.0000

Data Index: 243474 (C4 (Web Text))

Max Activating Token Index: 201

Text #2

Max Range: 3.5762. Min Range: -3.5762

Max Act: 2.2844. Min Act: -0.0000

Data Index: 1225303 (C4 (Web Text))

Max Activating Token Index: 6

Text #3

Max Range: 3.5762. Min Range: -3.5762

Max Act: 2.0301. Min Act: -0.0000

Data Index: 601194 (C4 (Web Text))

Max Activating Token Index: 588

Text #4

Max Range: 3.5762. Min Range: -3.5762

Max Act: 2.2154. Min Act: -0.0000

Data Index: 1337400 (C4 (Web Text))

Max Activating Token Index: 921

Text #5

Max Range: 3.5762. Min Range: -3.5762

Max Act: 2.0899. Min Act: -0.0000

Data Index: 301763 (C4 (Web Text))

Max Activating Token Index: 356

Text #6

Max Range: 3.5762. Min Range: -3.5762

Max Act: 2.0507. Min Act: -0.0000

Data Index: 138529 (C4 (Web Text))

Max Activating Token Index: 44

Text #7

Max Range: 3.5762. Min Range: -3.5762

Max Act: 2.0525. Min Act: -0.0000

Data Index: 914227 (C4 (Web Text))

Max Activating Token Index: 53

Text #8

Max Range: 3.5762. Min Range: -3.5762

Max Act: 1.9681. Min Act: -0.0000

Data Index: 814297 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 3.5762. Min Range: -3.5762

Max Act: 1.8452. Min Act: -0.0000

Data Index: 407587 (C4 (Web Text))

Max Activating Token Index: 329

Text #10

Max Range: 3.5762. Min Range: -3.5762

Max Act: 1.8626. Min Act: -0.0000

Data Index: 1517783 (Python Code)

Max Activating Token Index: 784

Text #11

Max Range: 3.5762. Min Range: -3.5762

Max Act: 1.6607. Min Act: -0.0000

Data Index: 579436 (C4 (Web Text))

Max Activating Token Index: 914

Text #12

Max Range: 3.5762. Min Range: -3.5762

Max Act: 1.8026. Min Act: -0.0000

Data Index: 597525 (C4 (Web Text))

Max Activating Token Index: 636

Text #13

Max Range: 3.5762. Min Range: -3.5762

Max Act: 1.7980. Min Act: -0.0000

Data Index: 174760 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 3.5762. Min Range: -3.5762

Max Act: 1.7996. Min Act: -0.0000

Data Index: 729275 (C4 (Web Text))

Max Activating Token Index: 386

Text #15

Max Range: 3.5762. Min Range: -3.5762

Max Act: 1.8681. Min Act: -0.0000

Data Index: 323274 (C4 (Web Text))

Max Activating Token Index: 421

Text #16

Max Range: 3.5762. Min Range: -3.5762

Max Act: 1.7628. Min Act: -0.0000

Data Index: 691298 (C4 (Web Text))

Max Activating Token Index: 631

Text #17

Max Range: 3.5762. Min Range: -3.5762

Max Act: 1.5614. Min Act: -0.0000

Data Index: 85920 (C4 (Web Text))

Max Activating Token Index: 765

Text #18

Max Range: 3.5762. Min Range: -3.5762

Max Act: 1.7357. Min Act: -0.0000

Data Index: 458581 (C4 (Web Text))

Max Activating Token Index: 594

Text #19

Max Range: 3.5762. Min Range: -3.5762

Max Act: 1.8073. Min Act: -0.0000

Data Index: 740390 (C4 (Web Text))

Max Activating Token Index: 734