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

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

Neuron 191 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0820. Min Act: -0.0002

Data Index: 1512611 (Python Code)

Max Activating Token Index: 123

Text #1

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0764. Min Act: -0.0002

Data Index: 1436142 (Python Code)

Max Activating Token Index: 161

Text #2

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0780. Min Act: -0.0003

Data Index: 67950 (C4 (Web Text))

Max Activating Token Index: 503

Text #3

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0810. Min Act: -0.0003

Data Index: 80678 (C4 (Web Text))

Max Activating Token Index: 811

Text #4

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0751. Min Act: -0.0002

Data Index: 1388825 (Python Code)

Max Activating Token Index: 288

Text #5

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0745. Min Act: -0.0003

Data Index: 1440848 (Python Code)

Max Activating Token Index: 311

Text #6

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0727. Min Act: -0.0003

Data Index: 1374587 (Python Code)

Max Activating Token Index: 44

Text #7

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0751. Min Act: -0.0003

Data Index: 1530108 (Python Code)

Max Activating Token Index: 305

Text #8

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0723. Min Act: -0.0002

Data Index: 1482550 (Python Code)

Max Activating Token Index: 508

Text #9

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0713. Min Act: -0.0002

Data Index: 1495077 (Python Code)

Max Activating Token Index: 580

Text #10

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0712. Min Act: -0.0002

Data Index: 1458142 (Python Code)

Max Activating Token Index: 395

Text #11

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0689. Min Act: -0.0002

Data Index: 1578277 (Python Code)

Max Activating Token Index: 491

Text #12

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0687. Min Act: -0.0002

Data Index: 1614110 (Python Code)

Max Activating Token Index: 144

Text #13

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0708. Min Act: -0.0002

Data Index: 1406364 (Python Code)

Max Activating Token Index: 378

Text #14

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0731. Min Act: -0.0002

Data Index: 1449447 (Python Code)

Max Activating Token Index: 82

Text #15

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0701. Min Act: -0.0002

Data Index: 1635261 (Python Code)

Max Activating Token Index: 583

Text #16

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0674. Min Act: -0.0002

Data Index: 1455600 (Python Code)

Max Activating Token Index: 717

Text #17

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0722. Min Act: -0.0003

Data Index: 1556179 (Python Code)

Max Activating Token Index: 186

Text #18

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0720. Min Act: -0.0003

Data Index: 1504365 (Python Code)

Max Activating Token Index: 524

Text #19

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0673. Min Act: -0.0002

Data Index: 1425664 (Python Code)

Max Activating Token Index: 66