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

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

Neuron 3511 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.8668. Min Act: -0.0000

Data Index: 95333 (C4 (Web Text))

Max Activating Token Index: 821

Text #1

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.8138. Min Act: -0.0000

Data Index: 1261935 (C4 (Web Text))

Max Activating Token Index: 517

Text #2

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.8254. Min Act: -0.0000

Data Index: 245773 (C4 (Web Text))

Max Activating Token Index: 366

Text #3

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.7643. Min Act: -0.0000

Data Index: 527959 (C4 (Web Text))

Max Activating Token Index: 22

Text #4

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.7353. Min Act: -0.0000

Data Index: 538888 (C4 (Web Text))

Max Activating Token Index: 181

Text #5

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.7248. Min Act: -0.0000

Data Index: 1162743 (C4 (Web Text))

Max Activating Token Index: 168

Text #6

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.7529. Min Act: -0.0000

Data Index: 132897 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.7270. Min Act: -0.0000

Data Index: 998816 (C4 (Web Text))

Max Activating Token Index: 79

Text #8

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.7246. Min Act: -0.0000

Data Index: 303391 (C4 (Web Text))

Max Activating Token Index: 128

Text #9

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.6536. Min Act: -0.0000

Data Index: 1288332 (C4 (Web Text))

Max Activating Token Index: 768

Text #10

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.6649. Min Act: -0.0000

Data Index: 545688 (C4 (Web Text))

Max Activating Token Index: 643

Text #11

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.6612. Min Act: -0.0000

Data Index: 397206 (C4 (Web Text))

Max Activating Token Index: 668

Text #12

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.7059. Min Act: -0.0000

Data Index: 768783 (C4 (Web Text))

Max Activating Token Index: 67

Text #13

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.6796. Min Act: -0.0000

Data Index: 1164200 (C4 (Web Text))

Max Activating Token Index: 17

Text #14

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.6459. Min Act: -0.0000

Data Index: 1091077 (C4 (Web Text))

Max Activating Token Index: 29

Text #15

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.6648. Min Act: -0.0000

Data Index: 968378 (C4 (Web Text))

Max Activating Token Index: 460

Text #16

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.6470. Min Act: -0.0000

Data Index: 1171041 (C4 (Web Text))

Max Activating Token Index: 324

Text #17

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.6727. Min Act: -0.0000

Data Index: 651304 (C4 (Web Text))

Max Activating Token Index: 1022

Text #18

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.6512. Min Act: -0.0000

Data Index: 1287450 (C4 (Web Text))

Max Activating Token Index: 971

Text #19

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.6288. Min Act: -0.0000

Data Index: 718771 (C4 (Web Text))

Max Activating Token Index: 636