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

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

Neuron 2601 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0472. Min Range: -1.0472

Max Act: 1.0392. Min Act: -0.0003

Data Index: 919888 (C4 (Web Text))

Max Activating Token Index: 915

Text #1

Max Range: 1.0472. Min Range: -1.0472

Max Act: 0.9832. Min Act: -0.0003

Data Index: 562436 (C4 (Web Text))

Max Activating Token Index: 623

Text #2

Max Range: 1.0472. Min Range: -1.0472

Max Act: 1.0472. Min Act: -0.0003

Data Index: 575648 (C4 (Web Text))

Max Activating Token Index: 821

Text #3

Max Range: 1.0472. Min Range: -1.0472

Max Act: 0.9110. Min Act: -0.0003

Data Index: 1123395 (C4 (Web Text))

Max Activating Token Index: 914

Text #4

Max Range: 1.0472. Min Range: -1.0472

Max Act: 0.9602. Min Act: -0.0003

Data Index: 323995 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 1.0472. Min Range: -1.0472

Max Act: 0.9989. Min Act: -0.0003

Data Index: 538578 (C4 (Web Text))

Max Activating Token Index: 770

Text #6

Max Range: 1.0472. Min Range: -1.0472

Max Act: 0.8940. Min Act: -0.0003

Data Index: 178927 (C4 (Web Text))

Max Activating Token Index: 883

Text #7

Max Range: 1.0472. Min Range: -1.0472

Max Act: 0.8936. Min Act: -0.0003

Data Index: 531039 (C4 (Web Text))

Max Activating Token Index: 689

Text #8

Max Range: 1.0472. Min Range: -1.0472

Max Act: 0.8988. Min Act: -0.0003

Data Index: 219021 (C4 (Web Text))

Max Activating Token Index: 709

Text #9

Max Range: 1.0472. Min Range: -1.0472

Max Act: 0.9012. Min Act: -0.0003

Data Index: 241424 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 1.0472. Min Range: -1.0472

Max Act: 0.8835. Min Act: -0.0003

Data Index: 885367 (C4 (Web Text))

Max Activating Token Index: 751

Text #11

Max Range: 1.0472. Min Range: -1.0472

Max Act: 0.9066. Min Act: -0.0003

Data Index: 447382 (C4 (Web Text))

Max Activating Token Index: 425

Text #12

Max Range: 1.0472. Min Range: -1.0472

Max Act: 0.7892. Min Act: -0.0003

Data Index: 485938 (C4 (Web Text))

Max Activating Token Index: 715

Text #13

Max Range: 1.0472. Min Range: -1.0472

Max Act: 0.8592. Min Act: -0.0003

Data Index: 992762 (C4 (Web Text))

Max Activating Token Index: 986

Text #14

Max Range: 1.0472. Min Range: -1.0472

Max Act: 0.7445. Min Act: -0.0003

Data Index: 539340 (C4 (Web Text))

Max Activating Token Index: 592

Text #15

Max Range: 1.0472. Min Range: -1.0472

Max Act: 0.7446. Min Act: -0.0003

Data Index: 125534 (C4 (Web Text))

Max Activating Token Index: 349

Text #16

Max Range: 1.0472. Min Range: -1.0472

Max Act: 0.8644. Min Act: -0.0003

Data Index: 1333271 (C4 (Web Text))

Max Activating Token Index: 73

Text #17

Max Range: 1.0472. Min Range: -1.0472

Max Act: 0.8606. Min Act: -0.0003

Data Index: 427018 (C4 (Web Text))

Max Activating Token Index: 868

Text #18

Max Range: 1.0472. Min Range: -1.0472

Max Act: 0.8523. Min Act: -0.0003

Data Index: 1207335 (C4 (Web Text))

Max Activating Token Index: 744

Text #19

Max Range: 1.0472. Min Range: -1.0472

Max Act: 0.8159. Min Act: -0.0003

Data Index: 237682 (C4 (Web Text))

Max Activating Token Index: 172