Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1997 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0019. Min Act: -0.0003

Data Index: 32867 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0018. Min Act: -0.0003

Data Index: 98322 (C4 (Web Text))

Max Activating Token Index: 847

Text #2

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0017. Min Act: -0.0003

Data Index: 225575 (C4 (Web Text))

Max Activating Token Index: 774

Text #3

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0017. Min Act: -0.0003

Data Index: 46827 (C4 (Web Text))

Max Activating Token Index: 632

Text #4

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0017. Min Act: -0.0004

Data Index: 187819 (C4 (Web Text))

Max Activating Token Index: 27

Text #5

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0016. Min Act: -0.0003

Data Index: 42227 (C4 (Web Text))

Max Activating Token Index: 306

Text #6

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0017. Min Act: -0.0003

Data Index: 541606 (C4 (Web Text))

Max Activating Token Index: 414

Text #7

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0017. Min Act: -0.0003

Data Index: 549290 (C4 (Web Text))

Max Activating Token Index: 849

Text #8

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0017. Min Act: -0.0003

Data Index: 726460 (C4 (Web Text))

Max Activating Token Index: 178

Text #9

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0016. Min Act: -0.0003

Data Index: 1307470 (C4 (Web Text))

Max Activating Token Index: 529

Text #10

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0018. Min Act: -0.0003

Data Index: 937351 (C4 (Web Text))

Max Activating Token Index: 343

Text #11

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0016. Min Act: -0.0003

Data Index: 1269115 (C4 (Web Text))

Max Activating Token Index: 196

Text #12

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0017. Min Act: -0.0003

Data Index: 1416218 (Python Code)

Max Activating Token Index: 632

Text #13

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0016. Min Act: -0.0003

Data Index: 1188868 (C4 (Web Text))

Max Activating Token Index: 628

Text #14

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0016. Min Act: -0.0003

Data Index: 74600 (C4 (Web Text))

Max Activating Token Index: 594

Text #15

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0016. Min Act: -0.0003

Data Index: 469212 (C4 (Web Text))

Max Activating Token Index: 228

Text #16

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0016. Min Act: -0.0003

Data Index: 1273511 (C4 (Web Text))

Max Activating Token Index: 339

Text #17

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0016. Min Act: -0.0003

Data Index: 1087745 (C4 (Web Text))

Max Activating Token Index: 259

Text #18

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0016. Min Act: -0.0003

Data Index: 204481 (C4 (Web Text))

Max Activating Token Index: 57

Text #19

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0015. Min Act: -0.0003

Data Index: 262743 (C4 (Web Text))

Max Activating Token Index: 300