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

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

Neuron 3065 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0030. Min Range: -0.0030

Max Act: 0.0030. Min Act: -0.0000

Data Index: 475405 (C4 (Web Text))

Max Activating Token Index: 489

Text #1

Max Range: 0.0030. Min Range: -0.0030

Max Act: 0.0024. Min Act: -0.0000

Data Index: 616070 (C4 (Web Text))

Max Activating Token Index: 433

Text #2

Max Range: 0.0030. Min Range: -0.0030

Max Act: 0.0015. Min Act: -0.0001

Data Index: 1218738 (C4 (Web Text))

Max Activating Token Index: 705

Text #3

Max Range: 0.0030. Min Range: -0.0030

Max Act: 0.0019. Min Act: -0.0000

Data Index: 130567 (C4 (Web Text))

Max Activating Token Index: 1022

Text #4

Max Range: 0.0030. Min Range: -0.0030

Max Act: 0.0022. Min Act: -0.0000

Data Index: 1261513 (C4 (Web Text))

Max Activating Token Index: 291

Text #5

Max Range: 0.0030. Min Range: -0.0030

Max Act: 0.0020. Min Act: -0.0001

Data Index: 1460402 (Python Code)

Max Activating Token Index: 597

Text #6

Max Range: 0.0030. Min Range: -0.0030

Max Act: 0.0021. Min Act: -0.0000

Data Index: 211380 (C4 (Web Text))

Max Activating Token Index: 78

Text #7

Max Range: 0.0030. Min Range: -0.0030

Max Act: 0.0016. Min Act: -0.0000

Data Index: 1447801 (Python Code)

Max Activating Token Index: 135

Text #8

Max Range: 0.0030. Min Range: -0.0030

Max Act: 0.0019. Min Act: -0.0000

Data Index: 1109012 (C4 (Web Text))

Max Activating Token Index: 562

Text #9

Max Range: 0.0030. Min Range: -0.0030

Max Act: 0.0016. Min Act: -0.0001

Data Index: 1322754 (C4 (Web Text))

Max Activating Token Index: 250

Text #10

Max Range: 0.0030. Min Range: -0.0030

Max Act: 0.0020. Min Act: -0.0000

Data Index: 137834 (C4 (Web Text))

Max Activating Token Index: 1019

Text #11

Max Range: 0.0030. Min Range: -0.0030

Max Act: 0.0015. Min Act: -0.0001

Data Index: 191195 (C4 (Web Text))

Max Activating Token Index: 258

Text #12

Max Range: 0.0030. Min Range: -0.0030

Max Act: 0.0015. Min Act: -0.0000

Data Index: 683319 (C4 (Web Text))

Max Activating Token Index: 718

Text #13

Max Range: 0.0030. Min Range: -0.0030

Max Act: 0.0014. Min Act: -0.0000

Data Index: 1028902 (C4 (Web Text))

Max Activating Token Index: 1020

Text #14

Max Range: 0.0030. Min Range: -0.0030

Max Act: 0.0018. Min Act: -0.0001

Data Index: 1154307 (C4 (Web Text))

Max Activating Token Index: 862

Text #15

Max Range: 0.0030. Min Range: -0.0030

Max Act: 0.0014. Min Act: -0.0000

Data Index: 391432 (C4 (Web Text))

Max Activating Token Index: 311

Text #16

Max Range: 0.0030. Min Range: -0.0030

Max Act: 0.0015. Min Act: -0.0000

Data Index: 1471017 (Python Code)

Max Activating Token Index: 997

Text #17

Max Range: 0.0030. Min Range: -0.0030

Max Act: 0.0017. Min Act: -0.0000

Data Index: 817293 (C4 (Web Text))

Max Activating Token Index: 401

Text #18

Max Range: 0.0030. Min Range: -0.0030

Max Act: 0.0016. Min Act: -0.0001

Data Index: 1386025 (Python Code)

Max Activating Token Index: 504

Text #19

Max Range: 0.0030. Min Range: -0.0030

Max Act: 0.0013. Min Act: -0.0000

Data Index: 239927 (C4 (Web Text))

Max Activating Token Index: 660