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

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

Neuron 104 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.8553. Min Act: -0.0000

Data Index: 1356152 (C4 (Web Text))

Max Activating Token Index: 810

Text #1

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.7820. Min Act: -0.0000

Data Index: 485067 (C4 (Web Text))

Max Activating Token Index: 224

Text #2

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.7685. Min Act: -0.0000

Data Index: 1149585 (C4 (Web Text))

Max Activating Token Index: 170

Text #3

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.7640. Min Act: -0.0000

Data Index: 704329 (C4 (Web Text))

Max Activating Token Index: 760

Text #4

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.7492. Min Act: -0.0000

Data Index: 816459 (C4 (Web Text))

Max Activating Token Index: 852

Text #5

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.7252. Min Act: -0.0001

Data Index: 11091 (C4 (Web Text))

Max Activating Token Index: 541

Text #6

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.6935. Min Act: -0.0001

Data Index: 508297 (C4 (Web Text))

Max Activating Token Index: 862

Text #7

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.7007. Min Act: -0.0000

Data Index: 778631 (C4 (Web Text))

Max Activating Token Index: 255

Text #8

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.6969. Min Act: -0.0001

Data Index: 240390 (C4 (Web Text))

Max Activating Token Index: 968

Text #9

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.6991. Min Act: -0.0001

Data Index: 1321254 (C4 (Web Text))

Max Activating Token Index: 733

Text #10

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.6657. Min Act: -0.0001

Data Index: 730881 (C4 (Web Text))

Max Activating Token Index: 755

Text #11

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.6830. Min Act: -0.0001

Data Index: 211968 (C4 (Web Text))

Max Activating Token Index: 781

Text #12

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.6293. Min Act: -0.0000

Data Index: 968456 (C4 (Web Text))

Max Activating Token Index: 513

Text #13

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.6265. Min Act: -0.0000

Data Index: 390124 (C4 (Web Text))

Max Activating Token Index: 695

Text #14

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.6937. Min Act: -0.0001

Data Index: 265954 (C4 (Web Text))

Max Activating Token Index: 1001

Text #15

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.6908. Min Act: -0.0001

Data Index: 606039 (C4 (Web Text))

Max Activating Token Index: 41

Text #16

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.5841. Min Act: -0.0001

Data Index: 465167 (C4 (Web Text))

Max Activating Token Index: 274

Text #17

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.6444. Min Act: -0.0000

Data Index: 322621 (C4 (Web Text))

Max Activating Token Index: 833

Text #18

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.6599. Min Act: -0.0001

Data Index: 681367 (C4 (Web Text))

Max Activating Token Index: 18

Text #19

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.6525. Min Act: -0.0000

Data Index: 623863 (C4 (Web Text))

Max Activating Token Index: 398