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

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

Neuron 1696 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7561. Min Range: -3.7561

Max Act: 2.9017. Min Act: -0.0000

Data Index: 922009 (C4 (Web Text))

Max Activating Token Index: 303

Text #1

Max Range: 3.7561. Min Range: -3.7561

Max Act: 3.5316. Min Act: -0.0000

Data Index: 1414910 (Python Code)

Max Activating Token Index: 945

Text #2

Max Range: 3.7561. Min Range: -3.7561

Max Act: 2.9092. Min Act: -0.0000

Data Index: 1465120 (Python Code)

Max Activating Token Index: 993

Text #3

Max Range: 3.7561. Min Range: -3.7561

Max Act: 2.3755. Min Act: -0.0000

Data Index: 1376425 (Python Code)

Max Activating Token Index: 222

Text #4

Max Range: 3.7561. Min Range: -3.7561

Max Act: 2.8034. Min Act: -0.0000

Data Index: 1365717 (Python Code)

Max Activating Token Index: 264

Text #5

Max Range: 3.7561. Min Range: -3.7561

Max Act: 3.7561. Min Act: -0.0000

Data Index: 272765 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 3.7561. Min Range: -3.7561

Max Act: 2.7062. Min Act: -0.0000

Data Index: 111083 (C4 (Web Text))

Max Activating Token Index: 341

Text #7

Max Range: 3.7561. Min Range: -3.7561

Max Act: 2.8606. Min Act: -0.0000

Data Index: 885491 (C4 (Web Text))

Max Activating Token Index: 824

Text #8

Max Range: 3.7561. Min Range: -3.7561

Max Act: 2.6381. Min Act: -0.0000

Data Index: 441992 (C4 (Web Text))

Max Activating Token Index: 443

Text #9

Max Range: 3.7561. Min Range: -3.7561

Max Act: 2.5106. Min Act: -0.0000

Data Index: 1420498 (Python Code)

Max Activating Token Index: 1005

Text #10

Max Range: 3.7561. Min Range: -3.7561

Max Act: 2.7191. Min Act: -0.0000

Data Index: 341455 (C4 (Web Text))

Max Activating Token Index: 474

Text #11

Max Range: 3.7561. Min Range: -3.7561

Max Act: 2.5324. Min Act: -0.0000

Data Index: 870117 (C4 (Web Text))

Max Activating Token Index: 717

Text #12

Max Range: 3.7561. Min Range: -3.7561

Max Act: 2.3272. Min Act: -0.0000

Data Index: 1447313 (Python Code)

Max Activating Token Index: 753

Text #13

Max Range: 3.7561. Min Range: -3.7561

Max Act: 2.4254. Min Act: -0.0000

Data Index: 1418281 (Python Code)

Max Activating Token Index: 439

Text #14

Max Range: 3.7561. Min Range: -3.7561

Max Act: 2.8877. Min Act: -0.0000

Data Index: 1608315 (Python Code)

Max Activating Token Index: 590

Text #15

Max Range: 3.7561. Min Range: -3.7561

Max Act: 2.7683. Min Act: -0.0000

Data Index: 540861 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 3.7561. Min Range: -3.7561

Max Act: 2.7542. Min Act: -0.0000

Data Index: 1427073 (Python Code)

Max Activating Token Index: 836

Text #17

Max Range: 3.7561. Min Range: -3.7561

Max Act: 2.3961. Min Act: -0.0000

Data Index: 1108615 (C4 (Web Text))

Max Activating Token Index: 958

Text #18

Max Range: 3.7561. Min Range: -3.7561

Max Act: 2.8794. Min Act: -0.0000

Data Index: 1538768 (Python Code)

Max Activating Token Index: 310

Text #19

Max Range: 3.7561. Min Range: -3.7561

Max Act: 2.5987. Min Act: -0.0000

Data Index: 54611 (C4 (Web Text))

Max Activating Token Index: 436