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

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

Neuron 3828 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8590. Min Range: -0.8590

Max Act: 0.8590. Min Act: -0.0001

Data Index: 299639 (C4 (Web Text))

Max Activating Token Index: 36

Text #1

Max Range: 0.8590. Min Range: -0.8590

Max Act: 0.8352. Min Act: -0.0001

Data Index: 969679 (C4 (Web Text))

Max Activating Token Index: 380

Text #2

Max Range: 0.8590. Min Range: -0.8590

Max Act: 0.8464. Min Act: -0.0001

Data Index: 412928 (C4 (Web Text))

Max Activating Token Index: 107

Text #3

Max Range: 0.8590. Min Range: -0.8590

Max Act: 0.7901. Min Act: -0.0001

Data Index: 1239073 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 0.8590. Min Range: -0.8590

Max Act: 0.8087. Min Act: -0.0001

Data Index: 49749 (C4 (Web Text))

Max Activating Token Index: 77

Text #5

Max Range: 0.8590. Min Range: -0.8590

Max Act: 0.7400. Min Act: -0.0001

Data Index: 1244008 (C4 (Web Text))

Max Activating Token Index: 102

Text #6

Max Range: 0.8590. Min Range: -0.8590

Max Act: 0.7702. Min Act: -0.0001

Data Index: 657414 (C4 (Web Text))

Max Activating Token Index: 592

Text #7

Max Range: 0.8590. Min Range: -0.8590

Max Act: 0.7224. Min Act: -0.0001

Data Index: 553376 (C4 (Web Text))

Max Activating Token Index: 1021

Text #8

Max Range: 0.8590. Min Range: -0.8590

Max Act: 0.6914. Min Act: -0.0001

Data Index: 877736 (C4 (Web Text))

Max Activating Token Index: 334

Text #9

Max Range: 0.8590. Min Range: -0.8590

Max Act: 0.6635. Min Act: -0.0001

Data Index: 555067 (C4 (Web Text))

Max Activating Token Index: 239

Text #10

Max Range: 0.8590. Min Range: -0.8590

Max Act: 0.7254. Min Act: -0.0001

Data Index: 586072 (C4 (Web Text))

Max Activating Token Index: 816

Text #11

Max Range: 0.8590. Min Range: -0.8590

Max Act: 0.6814. Min Act: -0.0001

Data Index: 438340 (C4 (Web Text))

Max Activating Token Index: 239

Text #12

Max Range: 0.8590. Min Range: -0.8590

Max Act: 0.6983. Min Act: -0.0001

Data Index: 526739 (C4 (Web Text))

Max Activating Token Index: 658

Text #13

Max Range: 0.8590. Min Range: -0.8590

Max Act: 0.6832. Min Act: -0.0001

Data Index: 1348564 (C4 (Web Text))

Max Activating Token Index: 680

Text #14

Max Range: 0.8590. Min Range: -0.8590

Max Act: 0.6968. Min Act: -0.0001

Data Index: 676045 (C4 (Web Text))

Max Activating Token Index: 460

Text #15

Max Range: 0.8590. Min Range: -0.8590

Max Act: 0.6765. Min Act: -0.0001

Data Index: 133571 (C4 (Web Text))

Max Activating Token Index: 575

Text #16

Max Range: 0.8590. Min Range: -0.8590

Max Act: 0.6678. Min Act: -0.0001

Data Index: 1047662 (C4 (Web Text))

Max Activating Token Index: 729

Text #17

Max Range: 0.8590. Min Range: -0.8590

Max Act: 0.6309. Min Act: -0.0001

Data Index: 582336 (C4 (Web Text))

Max Activating Token Index: 713

Text #18

Max Range: 0.8590. Min Range: -0.8590

Max Act: 0.7061. Min Act: -0.0001

Data Index: 481351 (C4 (Web Text))

Max Activating Token Index: 771

Text #19

Max Range: 0.8590. Min Range: -0.8590

Max Act: 0.7106. Min Act: -0.0001

Data Index: 1029459 (C4 (Web Text))

Max Activating Token Index: 621