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

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

Neuron 3861 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.8687. Min Act: -0.0003

Data Index: 1304632 (C4 (Web Text))

Max Activating Token Index: 448

Text #1

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.8209. Min Act: -0.0003

Data Index: 458512 (C4 (Web Text))

Max Activating Token Index: 848

Text #2

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.8031. Min Act: -0.0003

Data Index: 648251 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.6906. Min Act: -0.0003

Data Index: 112313 (C4 (Web Text))

Max Activating Token Index: 631

Text #4

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.6714. Min Act: -0.0003

Data Index: 225241 (C4 (Web Text))

Max Activating Token Index: 55

Text #5

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.6254. Min Act: -0.0003

Data Index: 479805 (C4 (Web Text))

Max Activating Token Index: 691

Text #6

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.6166. Min Act: -0.0003

Data Index: 736990 (C4 (Web Text))

Max Activating Token Index: 728

Text #7

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.5696. Min Act: -0.0003

Data Index: 20990 (C4 (Web Text))

Max Activating Token Index: 600

Text #8

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.5674. Min Act: -0.0003

Data Index: 900430 (C4 (Web Text))

Max Activating Token Index: 74

Text #9

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.6042. Min Act: -0.0003

Data Index: 531335 (C4 (Web Text))

Max Activating Token Index: 485

Text #10

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.5999. Min Act: -0.0003

Data Index: 52233 (C4 (Web Text))

Max Activating Token Index: 570

Text #11

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.5904. Min Act: -0.0003

Data Index: 528390 (C4 (Web Text))

Max Activating Token Index: 601

Text #12

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.6261. Min Act: -0.0003

Data Index: 1260277 (C4 (Web Text))

Max Activating Token Index: 880

Text #13

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.6246. Min Act: -0.0003

Data Index: 985459 (C4 (Web Text))

Max Activating Token Index: 719

Text #14

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.5743. Min Act: -0.0003

Data Index: 1200719 (C4 (Web Text))

Max Activating Token Index: 756

Text #15

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.5720. Min Act: -0.0003

Data Index: 1353627 (C4 (Web Text))

Max Activating Token Index: 161

Text #16

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.5706. Min Act: -0.0003

Data Index: 109314 (C4 (Web Text))

Max Activating Token Index: 729

Text #17

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.5648. Min Act: -0.0003

Data Index: 663436 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.5273. Min Act: -0.0003

Data Index: 326582 (C4 (Web Text))

Max Activating Token Index: 116

Text #19

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.5622. Min Act: -0.0003

Data Index: 390135 (C4 (Web Text))

Max Activating Token Index: 765