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

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

Neuron 1437 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9003. Min Range: -0.9003

Max Act: 0.9003. Min Act: -0.0003

Data Index: 789885 (C4 (Web Text))

Max Activating Token Index: 815

Text #1

Max Range: 0.9003. Min Range: -0.9003

Max Act: 0.8815. Min Act: -0.0002

Data Index: 1118745 (C4 (Web Text))

Max Activating Token Index: 707

Text #2

Max Range: 0.9003. Min Range: -0.9003

Max Act: 0.8726. Min Act: -0.0002

Data Index: 420377 (C4 (Web Text))

Max Activating Token Index: 317

Text #3

Max Range: 0.9003. Min Range: -0.9003

Max Act: 0.7538. Min Act: -0.0003

Data Index: 392080 (C4 (Web Text))

Max Activating Token Index: 908

Text #4

Max Range: 0.9003. Min Range: -0.9003

Max Act: 0.7912. Min Act: -0.0003

Data Index: 1306683 (C4 (Web Text))

Max Activating Token Index: 524

Text #5

Max Range: 0.9003. Min Range: -0.9003

Max Act: 0.7581. Min Act: -0.0003

Data Index: 879372 (C4 (Web Text))

Max Activating Token Index: 8

Text #6

Max Range: 0.9003. Min Range: -0.9003

Max Act: 0.7581. Min Act: -0.0003

Data Index: 452594 (C4 (Web Text))

Max Activating Token Index: 602

Text #7

Max Range: 0.9003. Min Range: -0.9003

Max Act: 0.8253. Min Act: -0.0002

Data Index: 621825 (C4 (Web Text))

Max Activating Token Index: 659

Text #8

Max Range: 0.9003. Min Range: -0.9003

Max Act: 0.7732. Min Act: -0.0003

Data Index: 341056 (C4 (Web Text))

Max Activating Token Index: 351

Text #9

Max Range: 0.9003. Min Range: -0.9003

Max Act: 0.7954. Min Act: -0.0003

Data Index: 1266341 (C4 (Web Text))

Max Activating Token Index: 585

Text #10

Max Range: 0.9003. Min Range: -0.9003

Max Act: 0.7766. Min Act: -0.0003

Data Index: 584467 (C4 (Web Text))

Max Activating Token Index: 687

Text #11

Max Range: 0.9003. Min Range: -0.9003

Max Act: 0.7680. Min Act: -0.0003

Data Index: 369229 (C4 (Web Text))

Max Activating Token Index: 802

Text #12

Max Range: 0.9003. Min Range: -0.9003

Max Act: 0.7414. Min Act: -0.0003

Data Index: 1229345 (C4 (Web Text))

Max Activating Token Index: 160

Text #13

Max Range: 0.9003. Min Range: -0.9003

Max Act: 0.7324. Min Act: -0.0003

Data Index: 1286514 (C4 (Web Text))

Max Activating Token Index: 195

Text #14

Max Range: 0.9003. Min Range: -0.9003

Max Act: 0.7182. Min Act: -0.0003

Data Index: 225767 (C4 (Web Text))

Max Activating Token Index: 306

Text #15

Max Range: 0.9003. Min Range: -0.9003

Max Act: 0.7254. Min Act: -0.0002

Data Index: 956802 (C4 (Web Text))

Max Activating Token Index: 125

Text #16

Max Range: 0.9003. Min Range: -0.9003

Max Act: 0.7183. Min Act: -0.0003

Data Index: 900732 (C4 (Web Text))

Max Activating Token Index: 79

Text #17

Max Range: 0.9003. Min Range: -0.9003

Max Act: 0.7368. Min Act: -0.0003

Data Index: 370129 (C4 (Web Text))

Max Activating Token Index: 306

Text #18

Max Range: 0.9003. Min Range: -0.9003

Max Act: 0.7137. Min Act: -0.0003

Data Index: 106976 (C4 (Web Text))

Max Activating Token Index: 742

Text #19

Max Range: 0.9003. Min Range: -0.9003

Max Act: 0.7122. Min Act: -0.0003

Data Index: 1100105 (C4 (Web Text))

Max Activating Token Index: 522