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

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

Neuron 4587 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5640. Min Range: -2.5640

Max Act: 2.5640. Min Act: -0.0000

Data Index: 1623541 (Python Code)

Max Activating Token Index: 69

Text #1

Max Range: 2.5640. Min Range: -2.5640

Max Act: 2.1082. Min Act: -0.0000

Data Index: 1524014 (Python Code)

Max Activating Token Index: 942

Text #2

Max Range: 2.5640. Min Range: -2.5640

Max Act: 1.9541. Min Act: -0.0000

Data Index: 1477546 (Python Code)

Max Activating Token Index: 425

Text #3

Max Range: 2.5640. Min Range: -2.5640

Max Act: 2.0413. Min Act: -0.0000

Data Index: 1513523 (Python Code)

Max Activating Token Index: 891

Text #4

Max Range: 2.5640. Min Range: -2.5640

Max Act: 2.0398. Min Act: -0.0000

Data Index: 1428646 (Python Code)

Max Activating Token Index: 347

Text #5

Max Range: 2.5640. Min Range: -2.5640

Max Act: 1.9615. Min Act: -0.0000

Data Index: 1603688 (Python Code)

Max Activating Token Index: 956

Text #6

Max Range: 2.5640. Min Range: -2.5640

Max Act: 2.0736. Min Act: -0.0000

Data Index: 32165 (C4 (Web Text))

Max Activating Token Index: 699

Text #7

Max Range: 2.5640. Min Range: -2.5640

Max Act: 1.8497. Min Act: -0.0000

Data Index: 962673 (C4 (Web Text))

Max Activating Token Index: 840

Text #8

Max Range: 2.5640. Min Range: -2.5640

Max Act: 1.7454. Min Act: -0.0000

Data Index: 1327137 (C4 (Web Text))

Max Activating Token Index: 525

Text #9

Max Range: 2.5640. Min Range: -2.5640

Max Act: 1.7889. Min Act: -0.0000

Data Index: 1379384 (Python Code)

Max Activating Token Index: 37

Text #10

Max Range: 2.5640. Min Range: -2.5640

Max Act: 1.6696. Min Act: -0.0000

Data Index: 1643800 (Python Code)

Max Activating Token Index: 146

Text #11

Max Range: 2.5640. Min Range: -2.5640

Max Act: 1.7631. Min Act: -0.0000

Data Index: 783587 (C4 (Web Text))

Max Activating Token Index: 846

Text #12

Max Range: 2.5640. Min Range: -2.5640

Max Act: 1.7148. Min Act: -0.0000

Data Index: 989535 (C4 (Web Text))

Max Activating Token Index: 962

Text #13

Max Range: 2.5640. Min Range: -2.5640

Max Act: 1.5304. Min Act: -0.0000

Data Index: 1496758 (Python Code)

Max Activating Token Index: 628

Text #14

Max Range: 2.5640. Min Range: -2.5640

Max Act: 1.6920. Min Act: -0.0000

Data Index: 255460 (C4 (Web Text))

Max Activating Token Index: 450

Text #15

Max Range: 2.5640. Min Range: -2.5640

Max Act: 1.6045. Min Act: -0.0000

Data Index: 169955 (C4 (Web Text))

Max Activating Token Index: 14

Text #16

Max Range: 2.5640. Min Range: -2.5640

Max Act: 1.5612. Min Act: -0.0000

Data Index: 1132 (C4 (Web Text))

Max Activating Token Index: 426

Text #17

Max Range: 2.5640. Min Range: -2.5640

Max Act: 1.6265. Min Act: -0.0000

Data Index: 216344 (C4 (Web Text))

Max Activating Token Index: 218

Text #18

Max Range: 2.5640. Min Range: -2.5640

Max Act: 1.6363. Min Act: -0.0000

Data Index: 606447 (C4 (Web Text))

Max Activating Token Index: 819

Text #19

Max Range: 2.5640. Min Range: -2.5640

Max Act: 1.6104. Min Act: -0.0000

Data Index: 480783 (C4 (Web Text))

Max Activating Token Index: 221