Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3465 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9459. Min Range: -0.9459

Max Act: 0.9459. Min Act: -0.0001

Data Index: 757927 (C4 (Web Text))

Max Activating Token Index: 774

Text #1

Max Range: 0.9459. Min Range: -0.9459

Max Act: 0.8692. Min Act: -0.0001

Data Index: 459381 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 0.9459. Min Range: -0.9459

Max Act: 0.7716. Min Act: -0.0001

Data Index: 684951 (C4 (Web Text))

Max Activating Token Index: 339

Text #3

Max Range: 0.9459. Min Range: -0.9459

Max Act: 0.7593. Min Act: -0.0001

Data Index: 269378 (C4 (Web Text))

Max Activating Token Index: 437

Text #4

Max Range: 0.9459. Min Range: -0.9459

Max Act: 0.7736. Min Act: -0.0001

Data Index: 609963 (C4 (Web Text))

Max Activating Token Index: 991

Text #5

Max Range: 0.9459. Min Range: -0.9459

Max Act: 0.7179. Min Act: -0.0001

Data Index: 205872 (C4 (Web Text))

Max Activating Token Index: 825

Text #6

Max Range: 0.9459. Min Range: -0.9459

Max Act: 0.7298. Min Act: -0.0001

Data Index: 941154 (C4 (Web Text))

Max Activating Token Index: 241

Text #7

Max Range: 0.9459. Min Range: -0.9459

Max Act: 0.6949. Min Act: -0.0001

Data Index: 1307601 (C4 (Web Text))

Max Activating Token Index: 461

Text #8

Max Range: 0.9459. Min Range: -0.9459

Max Act: 0.7101. Min Act: -0.0001

Data Index: 1039450 (C4 (Web Text))

Max Activating Token Index: 739

Text #9

Max Range: 0.9459. Min Range: -0.9459

Max Act: 0.7891. Min Act: -0.0001

Data Index: 1311975 (C4 (Web Text))

Max Activating Token Index: 632

Text #10

Max Range: 0.9459. Min Range: -0.9459

Max Act: 0.7350. Min Act: -0.0001

Data Index: 166293 (C4 (Web Text))

Max Activating Token Index: 538

Text #11

Max Range: 0.9459. Min Range: -0.9459

Max Act: 0.6579. Min Act: -0.0001

Data Index: 1229168 (C4 (Web Text))

Max Activating Token Index: 781

Text #12

Max Range: 0.9459. Min Range: -0.9459

Max Act: 0.6948. Min Act: -0.0001

Data Index: 462386 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 0.9459. Min Range: -0.9459

Max Act: 0.7016. Min Act: -0.0001

Data Index: 324703 (C4 (Web Text))

Max Activating Token Index: 341

Text #14

Max Range: 0.9459. Min Range: -0.9459

Max Act: 0.7023. Min Act: -0.0001

Data Index: 508951 (C4 (Web Text))

Max Activating Token Index: 294

Text #15

Max Range: 0.9459. Min Range: -0.9459

Max Act: 0.6834. Min Act: -0.0001

Data Index: 719914 (C4 (Web Text))

Max Activating Token Index: 134

Text #16

Max Range: 0.9459. Min Range: -0.9459

Max Act: 0.6010. Min Act: -0.0001

Data Index: 989543 (C4 (Web Text))

Max Activating Token Index: 332

Text #17

Max Range: 0.9459. Min Range: -0.9459

Max Act: 0.6463. Min Act: -0.0001

Data Index: 663543 (C4 (Web Text))

Max Activating Token Index: 741

Text #18

Max Range: 0.9459. Min Range: -0.9459

Max Act: 0.5987. Min Act: -0.0001

Data Index: 507853 (C4 (Web Text))

Max Activating Token Index: 95

Text #19

Max Range: 0.9459. Min Range: -0.9459

Max Act: 0.6649. Min Act: -0.0001

Data Index: 275818 (C4 (Web Text))

Max Activating Token Index: 796