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

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

Neuron 3440 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7993. Min Range: -0.7993

Max Act: 0.7993. Min Act: -0.0000

Data Index: 671868 (C4 (Web Text))

Max Activating Token Index: 417

Text #1

Max Range: 0.7993. Min Range: -0.7993

Max Act: 0.7844. Min Act: -0.0000

Data Index: 179607 (C4 (Web Text))

Max Activating Token Index: 989

Text #2

Max Range: 0.7993. Min Range: -0.7993

Max Act: 0.7369. Min Act: -0.0000

Data Index: 306898 (C4 (Web Text))

Max Activating Token Index: 869

Text #3

Max Range: 0.7993. Min Range: -0.7993

Max Act: 0.7210. Min Act: -0.0000

Data Index: 541528 (C4 (Web Text))

Max Activating Token Index: 440

Text #4

Max Range: 0.7993. Min Range: -0.7993

Max Act: 0.7022. Min Act: -0.0000

Data Index: 1259740 (C4 (Web Text))

Max Activating Token Index: 593

Text #5

Max Range: 0.7993. Min Range: -0.7993

Max Act: 0.6967. Min Act: -0.0000

Data Index: 806156 (C4 (Web Text))

Max Activating Token Index: 969

Text #6

Max Range: 0.7993. Min Range: -0.7993

Max Act: 0.6253. Min Act: -0.0000

Data Index: 998342 (C4 (Web Text))

Max Activating Token Index: 591

Text #7

Max Range: 0.7993. Min Range: -0.7993

Max Act: 0.6903. Min Act: -0.0000

Data Index: 743960 (C4 (Web Text))

Max Activating Token Index: 531

Text #8

Max Range: 0.7993. Min Range: -0.7993

Max Act: 0.6269. Min Act: -0.0000

Data Index: 23704 (C4 (Web Text))

Max Activating Token Index: 750

Text #9

Max Range: 0.7993. Min Range: -0.7993

Max Act: 0.6255. Min Act: -0.0001

Data Index: 429122 (C4 (Web Text))

Max Activating Token Index: 463

Text #10

Max Range: 0.7993. Min Range: -0.7993

Max Act: 0.6617. Min Act: -0.0000

Data Index: 20118 (C4 (Web Text))

Max Activating Token Index: 711

Text #11

Max Range: 0.7993. Min Range: -0.7993

Max Act: 0.6218. Min Act: -0.0000

Data Index: 1346396 (C4 (Web Text))

Max Activating Token Index: 343

Text #12

Max Range: 0.7993. Min Range: -0.7993

Max Act: 0.5949. Min Act: -0.0000

Data Index: 1304929 (C4 (Web Text))

Max Activating Token Index: 471

Text #13

Max Range: 0.7993. Min Range: -0.7993

Max Act: 0.6135. Min Act: -0.0000

Data Index: 875679 (C4 (Web Text))

Max Activating Token Index: 623

Text #14

Max Range: 0.7993. Min Range: -0.7993

Max Act: 0.6279. Min Act: -0.0000

Data Index: 1058718 (C4 (Web Text))

Max Activating Token Index: 559

Text #15

Max Range: 0.7993. Min Range: -0.7993

Max Act: 0.5850. Min Act: -0.0000

Data Index: 205368 (C4 (Web Text))

Max Activating Token Index: 412

Text #16

Max Range: 0.7993. Min Range: -0.7993

Max Act: 0.5731. Min Act: -0.0000

Data Index: 1354703 (C4 (Web Text))

Max Activating Token Index: 405

Text #17

Max Range: 0.7993. Min Range: -0.7993

Max Act: 0.5696. Min Act: -0.0000

Data Index: 1273539 (C4 (Web Text))

Max Activating Token Index: 840

Text #18

Max Range: 0.7993. Min Range: -0.7993

Max Act: 0.5654. Min Act: -0.0001

Data Index: 215706 (C4 (Web Text))

Max Activating Token Index: 360

Text #19

Max Range: 0.7993. Min Range: -0.7993

Max Act: 0.5719. Min Act: -0.0000

Data Index: 427759 (C4 (Web Text))

Max Activating Token Index: 563