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

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

Neuron 610 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.5667. Min Act: -0.0000

Data Index: 1639124 (Python Code)

Max Activating Token Index: 583

Text #1

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.5409. Min Act: -0.0000

Data Index: 1496550 (Python Code)

Max Activating Token Index: 727

Text #2

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.5348. Min Act: -0.0000

Data Index: 1542146 (Python Code)

Max Activating Token Index: 969

Text #3

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.4983. Min Act: -0.0000

Data Index: 1552199 (Python Code)

Max Activating Token Index: 485

Text #4

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.4887. Min Act: -0.0000

Data Index: 1461912 (Python Code)

Max Activating Token Index: 331

Text #5

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.5057. Min Act: -0.0000

Data Index: 1510287 (Python Code)

Max Activating Token Index: 860

Text #6

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.5022. Min Act: -0.0000

Data Index: 1652283 (Python Code)

Max Activating Token Index: 594

Text #7

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.4994. Min Act: -0.0000

Data Index: 1514643 (Python Code)

Max Activating Token Index: 797

Text #8

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.4977. Min Act: -0.0000

Data Index: 1528806 (Python Code)

Max Activating Token Index: 91

Text #9

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.4577. Min Act: -0.0000

Data Index: 1467611 (Python Code)

Max Activating Token Index: 193

Text #10

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.5060. Min Act: -0.0000

Data Index: 1503607 (Python Code)

Max Activating Token Index: 52

Text #11

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.4891. Min Act: -0.0000

Data Index: 1401540 (Python Code)

Max Activating Token Index: 597

Text #12

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.4999. Min Act: -0.0000

Data Index: 1635225 (Python Code)

Max Activating Token Index: 597

Text #13

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.4672. Min Act: -0.0000

Data Index: 1596603 (Python Code)

Max Activating Token Index: 535

Text #14

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.4672. Min Act: -0.0000

Data Index: 1491880 (Python Code)

Max Activating Token Index: 528

Text #15

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.4509. Min Act: -0.0000

Data Index: 1477487 (Python Code)

Max Activating Token Index: 858

Text #16

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.4627. Min Act: -0.0000

Data Index: 1408566 (Python Code)

Max Activating Token Index: 64

Text #17

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.4740. Min Act: -0.0000

Data Index: 1362974 (Python Code)

Max Activating Token Index: 639

Text #18

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.4890. Min Act: -0.0000

Data Index: 1635442 (Python Code)

Max Activating Token Index: 584

Text #19

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.4877. Min Act: -0.0000

Data Index: 1594566 (Python Code)

Max Activating Token Index: 500