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

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

Neuron 822 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.4880. Min Act: -0.0001

Data Index: 461661 (C4 (Web Text))

Max Activating Token Index: 135

Text #1

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.4950. Min Act: -0.0001

Data Index: 844223 (C4 (Web Text))

Max Activating Token Index: 390

Text #2

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.4652. Min Act: -0.0001

Data Index: 1293320 (C4 (Web Text))

Max Activating Token Index: 604

Text #3

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.4850. Min Act: -0.0001

Data Index: 37875 (C4 (Web Text))

Max Activating Token Index: 516

Text #4

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.5183. Min Act: -0.0001

Data Index: 119635 (C4 (Web Text))

Max Activating Token Index: 637

Text #5

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.4748. Min Act: -0.0001

Data Index: 1341019 (C4 (Web Text))

Max Activating Token Index: 562

Text #6

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.4862. Min Act: -0.0001

Data Index: 1051406 (C4 (Web Text))

Max Activating Token Index: 917

Text #7

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.4423. Min Act: -0.0001

Data Index: 918115 (C4 (Web Text))

Max Activating Token Index: 707

Text #8

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.4471. Min Act: -0.0001

Data Index: 990766 (C4 (Web Text))

Max Activating Token Index: 1016

Text #9

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.4303. Min Act: -0.0001

Data Index: 558524 (C4 (Web Text))

Max Activating Token Index: 561

Text #10

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.4228. Min Act: -0.0001

Data Index: 769309 (C4 (Web Text))

Max Activating Token Index: 227

Text #11

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.4226. Min Act: -0.0001

Data Index: 990568 (C4 (Web Text))

Max Activating Token Index: 662

Text #12

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.3992. Min Act: -0.0001

Data Index: 1171440 (C4 (Web Text))

Max Activating Token Index: 673

Text #13

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.3884. Min Act: -0.0001

Data Index: 429544 (C4 (Web Text))

Max Activating Token Index: 452

Text #14

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.4029. Min Act: -0.0001

Data Index: 1015080 (C4 (Web Text))

Max Activating Token Index: 632

Text #15

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.3846. Min Act: -0.0001

Data Index: 509069 (C4 (Web Text))

Max Activating Token Index: 499

Text #16

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.3669. Min Act: -0.0001

Data Index: 1345352 (C4 (Web Text))

Max Activating Token Index: 810

Text #17

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.3706. Min Act: -0.0001

Data Index: 204057 (C4 (Web Text))

Max Activating Token Index: 365

Text #18

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.3784. Min Act: -0.0001

Data Index: 1069316 (C4 (Web Text))

Max Activating Token Index: 719

Text #19

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.3801. Min Act: -0.0001

Data Index: 1040491 (C4 (Web Text))

Max Activating Token Index: 573