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

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

Neuron 284 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7062. Min Range: -0.7062

Max Act: 0.7062. Min Act: -0.0000

Data Index: 6909 (C4 (Web Text))

Max Activating Token Index: 289

Text #1

Max Range: 0.7062. Min Range: -0.7062

Max Act: 0.4387. Min Act: -0.0000

Data Index: 330960 (C4 (Web Text))

Max Activating Token Index: 153

Text #2

Max Range: 0.7062. Min Range: -0.7062

Max Act: 0.4180. Min Act: -0.0000

Data Index: 746915 (C4 (Web Text))

Max Activating Token Index: 504

Text #3

Max Range: 0.7062. Min Range: -0.7062

Max Act: 0.4242. Min Act: -0.0000

Data Index: 775353 (C4 (Web Text))

Max Activating Token Index: 411

Text #4

Max Range: 0.7062. Min Range: -0.7062

Max Act: 0.3672. Min Act: -0.0000

Data Index: 831143 (C4 (Web Text))

Max Activating Token Index: 983

Text #5

Max Range: 0.7062. Min Range: -0.7062

Max Act: 0.3596. Min Act: -0.0000

Data Index: 1611187 (Python Code)

Max Activating Token Index: 89

Text #6

Max Range: 0.7062. Min Range: -0.7062

Max Act: 0.3599. Min Act: -0.0000

Data Index: 48889 (C4 (Web Text))

Max Activating Token Index: 152

Text #7

Max Range: 0.7062. Min Range: -0.7062

Max Act: 0.3912. Min Act: -0.0000

Data Index: 331391 (C4 (Web Text))

Max Activating Token Index: 978

Text #8

Max Range: 0.7062. Min Range: -0.7062

Max Act: 0.3725. Min Act: -0.0000

Data Index: 945856 (C4 (Web Text))

Max Activating Token Index: 644

Text #9

Max Range: 0.7062. Min Range: -0.7062

Max Act: 0.3596. Min Act: -0.0000

Data Index: 1046504 (C4 (Web Text))

Max Activating Token Index: 319

Text #10

Max Range: 0.7062. Min Range: -0.7062

Max Act: 0.3300. Min Act: -0.0000

Data Index: 418425 (C4 (Web Text))

Max Activating Token Index: 472

Text #11

Max Range: 0.7062. Min Range: -0.7062

Max Act: 0.3435. Min Act: -0.0000

Data Index: 1068088 (C4 (Web Text))

Max Activating Token Index: 927

Text #12

Max Range: 0.7062. Min Range: -0.7062

Max Act: 0.3364. Min Act: -0.0000

Data Index: 650374 (C4 (Web Text))

Max Activating Token Index: 1003

Text #13

Max Range: 0.7062. Min Range: -0.7062

Max Act: 0.1526. Min Act: -0.0000

Data Index: 1408626 (Python Code)

Max Activating Token Index: 976

Text #14

Max Range: 0.7062. Min Range: -0.7062

Max Act: 0.2971. Min Act: -0.0000

Data Index: 1468225 (Python Code)

Max Activating Token Index: 178

Text #15

Max Range: 0.7062. Min Range: -0.7062

Max Act: 0.3098. Min Act: -0.0000

Data Index: 765389 (C4 (Web Text))

Max Activating Token Index: 768

Text #16

Max Range: 0.7062. Min Range: -0.7062

Max Act: 0.2975. Min Act: -0.0000

Data Index: 1374841 (Python Code)

Max Activating Token Index: 597

Text #17

Max Range: 0.7062. Min Range: -0.7062

Max Act: 0.2729. Min Act: -0.0000

Data Index: 1485316 (Python Code)

Max Activating Token Index: 920

Text #18

Max Range: 0.7062. Min Range: -0.7062

Max Act: 0.2916. Min Act: -0.0000

Data Index: 609658 (C4 (Web Text))

Max Activating Token Index: 700

Text #19

Max Range: 0.7062. Min Range: -0.7062

Max Act: 0.2700. Min Act: -0.0000

Data Index: 1385666 (Python Code)

Max Activating Token Index: 681