Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1955 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0025. Min Act: -0.0005

Data Index: 881359 (C4 (Web Text))

Max Activating Token Index: 159

Text #1

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0022. Min Act: -0.0006

Data Index: 1364274 (Python Code)

Max Activating Token Index: 631

Text #2

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0022. Min Act: -0.0006

Data Index: 299728 (C4 (Web Text))

Max Activating Token Index: 254

Text #3

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0022. Min Act: -0.0006

Data Index: 1403647 (Python Code)

Max Activating Token Index: 869

Text #4

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0021. Min Act: -0.0006

Data Index: 137374 (C4 (Web Text))

Max Activating Token Index: 520

Text #5

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0021. Min Act: -0.0006

Data Index: 1536293 (Python Code)

Max Activating Token Index: 632

Text #6

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0020. Min Act: -0.0006

Data Index: 1626011 (Python Code)

Max Activating Token Index: 927

Text #7

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0020. Min Act: -0.0006

Data Index: 1500799 (Python Code)

Max Activating Token Index: 638

Text #8

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0020. Min Act: -0.0006

Data Index: 982235 (C4 (Web Text))

Max Activating Token Index: 528

Text #9

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0020. Min Act: -0.0006

Data Index: 1515130 (Python Code)

Max Activating Token Index: 476

Text #10

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0020. Min Act: -0.0005

Data Index: 198112 (C4 (Web Text))

Max Activating Token Index: 431

Text #11

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0019. Min Act: -0.0005

Data Index: 1028964 (C4 (Web Text))

Max Activating Token Index: 512

Text #12

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0020. Min Act: -0.0006

Data Index: 1606237 (Python Code)

Max Activating Token Index: 568

Text #13

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0020. Min Act: -0.0006

Data Index: 1491175 (Python Code)

Max Activating Token Index: 490

Text #14

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0019. Min Act: -0.0006

Data Index: 502843 (C4 (Web Text))

Max Activating Token Index: 370

Text #15

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0019. Min Act: -0.0006

Data Index: 1472830 (Python Code)

Max Activating Token Index: 202

Text #16

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0019. Min Act: -0.0006

Data Index: 1124822 (C4 (Web Text))

Max Activating Token Index: 445

Text #17

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0019. Min Act: -0.0006

Data Index: 1505514 (Python Code)

Max Activating Token Index: 425

Text #18

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0018. Min Act: -0.0005

Data Index: 889106 (C4 (Web Text))

Max Activating Token Index: 521

Text #19

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0018. Min Act: -0.0006

Data Index: 1407619 (Python Code)

Max Activating Token Index: 831