Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3893 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6859. Min Range: -0.6859

Max Act: 0.6859. Min Act: -0.0000

Data Index: 585336 (C4 (Web Text))

Max Activating Token Index: 513

Text #1

Max Range: 0.6859. Min Range: -0.6859

Max Act: 0.6269. Min Act: -0.0000

Data Index: 90425 (C4 (Web Text))

Max Activating Token Index: 491

Text #2

Max Range: 0.6859. Min Range: -0.6859

Max Act: 0.5832. Min Act: -0.0000

Data Index: 831931 (C4 (Web Text))

Max Activating Token Index: 451

Text #3

Max Range: 0.6859. Min Range: -0.6859

Max Act: 0.5779. Min Act: -0.0000

Data Index: 150080 (C4 (Web Text))

Max Activating Token Index: 688

Text #4

Max Range: 0.6859. Min Range: -0.6859

Max Act: 0.5522. Min Act: -0.0000

Data Index: 162194 (C4 (Web Text))

Max Activating Token Index: 490

Text #5

Max Range: 0.6859. Min Range: -0.6859

Max Act: 0.5711. Min Act: -0.0000

Data Index: 1003053 (C4 (Web Text))

Max Activating Token Index: 147

Text #6

Max Range: 0.6859. Min Range: -0.6859

Max Act: 0.5495. Min Act: -0.0000

Data Index: 1041140 (C4 (Web Text))

Max Activating Token Index: 673

Text #7

Max Range: 0.6859. Min Range: -0.6859

Max Act: 0.5275. Min Act: -0.0000

Data Index: 261241 (C4 (Web Text))

Max Activating Token Index: 768

Text #8

Max Range: 0.6859. Min Range: -0.6859

Max Act: 0.5079. Min Act: -0.0000

Data Index: 455733 (C4 (Web Text))

Max Activating Token Index: 738

Text #9

Max Range: 0.6859. Min Range: -0.6859

Max Act: 0.5436. Min Act: -0.0000

Data Index: 638068 (C4 (Web Text))

Max Activating Token Index: 972

Text #10

Max Range: 0.6859. Min Range: -0.6859

Max Act: 0.5347. Min Act: -0.0000

Data Index: 1336791 (C4 (Web Text))

Max Activating Token Index: 339

Text #11

Max Range: 0.6859. Min Range: -0.6859

Max Act: 0.5104. Min Act: -0.0000

Data Index: 603175 (C4 (Web Text))

Max Activating Token Index: 319

Text #12

Max Range: 0.6859. Min Range: -0.6859

Max Act: 0.5075. Min Act: -0.0000

Data Index: 403465 (C4 (Web Text))

Max Activating Token Index: 32

Text #13

Max Range: 0.6859. Min Range: -0.6859

Max Act: 0.4826. Min Act: -0.0000

Data Index: 686695 (C4 (Web Text))

Max Activating Token Index: 838

Text #14

Max Range: 0.6859. Min Range: -0.6859

Max Act: 0.4903. Min Act: -0.0000

Data Index: 699237 (C4 (Web Text))

Max Activating Token Index: 657

Text #15

Max Range: 0.6859. Min Range: -0.6859

Max Act: 0.5022. Min Act: -0.0000

Data Index: 49645 (C4 (Web Text))

Max Activating Token Index: 973

Text #16

Max Range: 0.6859. Min Range: -0.6859

Max Act: 0.4995. Min Act: -0.0000

Data Index: 1048508 (C4 (Web Text))

Max Activating Token Index: 217

Text #17

Max Range: 0.6859. Min Range: -0.6859

Max Act: 0.4889. Min Act: -0.0000

Data Index: 1344581 (C4 (Web Text))

Max Activating Token Index: 1013

Text #18

Max Range: 0.6859. Min Range: -0.6859

Max Act: 0.4752. Min Act: -0.0000

Data Index: 146742 (C4 (Web Text))

Max Activating Token Index: 402

Text #19

Max Range: 0.6859. Min Range: -0.6859

Max Act: 0.4784. Min Act: -0.0000

Data Index: 902740 (C4 (Web Text))

Max Activating Token Index: 868