Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1435 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.3021. Min Range: -1.3021

Max Act: 1.1714. Min Act: -0.0003

Data Index: 1046523 (C4 (Web Text))

Max Activating Token Index: 735

Text #1

Max Range: 1.3021. Min Range: -1.3021

Max Act: 1.1998. Min Act: -0.0003

Data Index: 713999 (C4 (Web Text))

Max Activating Token Index: 788

Text #2

Max Range: 1.3021. Min Range: -1.3021

Max Act: 1.3021. Min Act: -0.0003

Data Index: 959316 (C4 (Web Text))

Max Activating Token Index: 200

Text #3

Max Range: 1.3021. Min Range: -1.3021

Max Act: 1.0209. Min Act: -0.0003

Data Index: 1120185 (C4 (Web Text))

Max Activating Token Index: 167

Text #4

Max Range: 1.3021. Min Range: -1.3021

Max Act: 1.0728. Min Act: -0.0003

Data Index: 521530 (C4 (Web Text))

Max Activating Token Index: 472

Text #5

Max Range: 1.3021. Min Range: -1.3021

Max Act: 1.0140. Min Act: -0.0003

Data Index: 1076608 (C4 (Web Text))

Max Activating Token Index: 630

Text #6

Max Range: 1.3021. Min Range: -1.3021

Max Act: 1.0842. Min Act: -0.0003

Data Index: 725855 (C4 (Web Text))

Max Activating Token Index: 719

Text #7

Max Range: 1.3021. Min Range: -1.3021

Max Act: 0.9755. Min Act: -0.0003

Data Index: 628838 (C4 (Web Text))

Max Activating Token Index: 933

Text #8

Max Range: 1.3021. Min Range: -1.3021

Max Act: 0.8803. Min Act: -0.0003

Data Index: 604245 (C4 (Web Text))

Max Activating Token Index: 571

Text #9

Max Range: 1.3021. Min Range: -1.3021

Max Act: 0.9028. Min Act: -0.0003

Data Index: 294342 (C4 (Web Text))

Max Activating Token Index: 729

Text #10

Max Range: 1.3021. Min Range: -1.3021

Max Act: 0.9258. Min Act: -0.0003

Data Index: 948034 (C4 (Web Text))

Max Activating Token Index: 376

Text #11

Max Range: 1.3021. Min Range: -1.3021

Max Act: 0.9191. Min Act: -0.0003

Data Index: 189173 (C4 (Web Text))

Max Activating Token Index: 67

Text #12

Max Range: 1.3021. Min Range: -1.3021

Max Act: 0.9154. Min Act: -0.0003

Data Index: 82540 (C4 (Web Text))

Max Activating Token Index: 178

Text #13

Max Range: 1.3021. Min Range: -1.3021

Max Act: 0.9658. Min Act: -0.0003

Data Index: 517226 (C4 (Web Text))

Max Activating Token Index: 331

Text #14

Max Range: 1.3021. Min Range: -1.3021

Max Act: 0.8978. Min Act: -0.0003

Data Index: 786738 (C4 (Web Text))

Max Activating Token Index: 212

Text #15

Max Range: 1.3021. Min Range: -1.3021

Max Act: 0.8671. Min Act: -0.0003

Data Index: 165261 (C4 (Web Text))

Max Activating Token Index: 733

Text #16

Max Range: 1.3021. Min Range: -1.3021

Max Act: 0.8878. Min Act: -0.0003

Data Index: 1272336 (C4 (Web Text))

Max Activating Token Index: 868

Text #17

Max Range: 1.3021. Min Range: -1.3021

Max Act: 1.0289. Min Act: -0.0003

Data Index: 940942 (C4 (Web Text))

Max Activating Token Index: 1009

Text #18

Max Range: 1.3021. Min Range: -1.3021

Max Act: 0.8973. Min Act: -0.0003

Data Index: 1023892 (C4 (Web Text))

Max Activating Token Index: 469

Text #19

Max Range: 1.3021. Min Range: -1.3021

Max Act: 0.8109. Min Act: -0.0003

Data Index: 688306 (C4 (Web Text))

Max Activating Token Index: 713