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

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

Neuron 2717 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5765. Min Range: -0.5765

Max Act: 0.5765. Min Act: -0.0000

Data Index: 1143711 (C4 (Web Text))

Max Activating Token Index: 389

Text #1

Max Range: 0.5765. Min Range: -0.5765

Max Act: 0.5068. Min Act: -0.0000

Data Index: 1038813 (C4 (Web Text))

Max Activating Token Index: 555

Text #2

Max Range: 0.5765. Min Range: -0.5765

Max Act: 0.4648. Min Act: -0.0000

Data Index: 27889 (C4 (Web Text))

Max Activating Token Index: 741

Text #3

Max Range: 0.5765. Min Range: -0.5765

Max Act: 0.5222. Min Act: -0.0000

Data Index: 914357 (C4 (Web Text))

Max Activating Token Index: 812

Text #4

Max Range: 0.5765. Min Range: -0.5765

Max Act: 0.4394. Min Act: -0.0000

Data Index: 579637 (C4 (Web Text))

Max Activating Token Index: 499

Text #5

Max Range: 0.5765. Min Range: -0.5765

Max Act: 0.4108. Min Act: -0.0000

Data Index: 41391 (C4 (Web Text))

Max Activating Token Index: 452

Text #6

Max Range: 0.5765. Min Range: -0.5765

Max Act: 0.3718. Min Act: -0.0000

Data Index: 745967 (C4 (Web Text))

Max Activating Token Index: 56

Text #7

Max Range: 0.5765. Min Range: -0.5765

Max Act: 0.3858. Min Act: -0.0000

Data Index: 255228 (C4 (Web Text))

Max Activating Token Index: 638

Text #8

Max Range: 0.5765. Min Range: -0.5765

Max Act: 0.3806. Min Act: -0.0000

Data Index: 598863 (C4 (Web Text))

Max Activating Token Index: 342

Text #9

Max Range: 0.5765. Min Range: -0.5765

Max Act: 0.3519. Min Act: -0.0000

Data Index: 668568 (C4 (Web Text))

Max Activating Token Index: 337

Text #10

Max Range: 0.5765. Min Range: -0.5765

Max Act: 0.3810. Min Act: -0.0000

Data Index: 195189 (C4 (Web Text))

Max Activating Token Index: 793

Text #11

Max Range: 0.5765. Min Range: -0.5765

Max Act: 0.3258. Min Act: -0.0000

Data Index: 1068035 (C4 (Web Text))

Max Activating Token Index: 757

Text #12

Max Range: 0.5765. Min Range: -0.5765

Max Act: 0.3484. Min Act: -0.0000

Data Index: 1215493 (C4 (Web Text))

Max Activating Token Index: 715

Text #13

Max Range: 0.5765. Min Range: -0.5765

Max Act: 0.3714. Min Act: -0.0000

Data Index: 62789 (C4 (Web Text))

Max Activating Token Index: 676

Text #14

Max Range: 0.5765. Min Range: -0.5765

Max Act: 0.3114. Min Act: -0.0000

Data Index: 163649 (C4 (Web Text))

Max Activating Token Index: 907

Text #15

Max Range: 0.5765. Min Range: -0.5765

Max Act: 0.3401. Min Act: -0.0000

Data Index: 1224544 (C4 (Web Text))

Max Activating Token Index: 645

Text #16

Max Range: 0.5765. Min Range: -0.5765

Max Act: 0.3291. Min Act: -0.0000

Data Index: 831029 (C4 (Web Text))

Max Activating Token Index: 311

Text #17

Max Range: 0.5765. Min Range: -0.5765

Max Act: 0.3116. Min Act: -0.0000

Data Index: 528127 (C4 (Web Text))

Max Activating Token Index: 236

Text #18

Max Range: 0.5765. Min Range: -0.5765

Max Act: 0.3333. Min Act: -0.0000

Data Index: 804967 (C4 (Web Text))

Max Activating Token Index: 168

Text #19

Max Range: 0.5765. Min Range: -0.5765

Max Act: 0.3172. Min Act: -0.0000

Data Index: 1070368 (C4 (Web Text))

Max Activating Token Index: 30