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

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

Neuron 5872 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4600. Min Range: -1.4600

Max Act: 1.4600. Min Act: -0.0000

Data Index: 461812 (C4 (Web Text))

Max Activating Token Index: 953

Text #1

Max Range: 1.4600. Min Range: -1.4600

Max Act: 1.1901. Min Act: -0.0000

Data Index: 892446 (C4 (Web Text))

Max Activating Token Index: 475

Text #2

Max Range: 1.4600. Min Range: -1.4600

Max Act: 1.1910. Min Act: -0.0000

Data Index: 1340598 (C4 (Web Text))

Max Activating Token Index: 935

Text #3

Max Range: 1.4600. Min Range: -1.4600

Max Act: 1.1469. Min Act: -0.0000

Data Index: 272051 (C4 (Web Text))

Max Activating Token Index: 333

Text #4

Max Range: 1.4600. Min Range: -1.4600

Max Act: 1.1079. Min Act: -0.0000

Data Index: 507159 (C4 (Web Text))

Max Activating Token Index: 297

Text #5

Max Range: 1.4600. Min Range: -1.4600

Max Act: 1.0169. Min Act: -0.0000

Data Index: 799034 (C4 (Web Text))

Max Activating Token Index: 719

Text #6

Max Range: 1.4600. Min Range: -1.4600

Max Act: 1.0684. Min Act: -0.0000

Data Index: 1278460 (C4 (Web Text))

Max Activating Token Index: 703

Text #7

Max Range: 1.4600. Min Range: -1.4600

Max Act: 1.0961. Min Act: -0.0000

Data Index: 763750 (C4 (Web Text))

Max Activating Token Index: 37

Text #8

Max Range: 1.4600. Min Range: -1.4600

Max Act: 1.0081. Min Act: -0.0000

Data Index: 370564 (C4 (Web Text))

Max Activating Token Index: 769

Text #9

Max Range: 1.4600. Min Range: -1.4600

Max Act: 0.9395. Min Act: -0.0000

Data Index: 523606 (C4 (Web Text))

Max Activating Token Index: 575

Text #10

Max Range: 1.4600. Min Range: -1.4600

Max Act: 0.9508. Min Act: -0.0000

Data Index: 797615 (C4 (Web Text))

Max Activating Token Index: 1010

Text #11

Max Range: 1.4600. Min Range: -1.4600

Max Act: 0.9385. Min Act: -0.0000

Data Index: 491994 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 1.4600. Min Range: -1.4600

Max Act: 0.9059. Min Act: -0.0000

Data Index: 147139 (C4 (Web Text))

Max Activating Token Index: 448

Text #13

Max Range: 1.4600. Min Range: -1.4600

Max Act: 0.9001. Min Act: -0.0000

Data Index: 1033465 (C4 (Web Text))

Max Activating Token Index: 961

Text #14

Max Range: 1.4600. Min Range: -1.4600

Max Act: 0.8673. Min Act: -0.0000

Data Index: 1064840 (C4 (Web Text))

Max Activating Token Index: 1004

Text #15

Max Range: 1.4600. Min Range: -1.4600

Max Act: 0.8630. Min Act: -0.0000

Data Index: 1439359 (Python Code)

Max Activating Token Index: 484

Text #16

Max Range: 1.4600. Min Range: -1.4600

Max Act: 0.8897. Min Act: -0.0000

Data Index: 48936 (C4 (Web Text))

Max Activating Token Index: 127

Text #17

Max Range: 1.4600. Min Range: -1.4600

Max Act: 0.8653. Min Act: -0.0000

Data Index: 1570712 (Python Code)

Max Activating Token Index: 285

Text #18

Max Range: 1.4600. Min Range: -1.4600

Max Act: 0.8623. Min Act: -0.0000

Data Index: 1396282 (Python Code)

Max Activating Token Index: 96

Text #19

Max Range: 1.4600. Min Range: -1.4600

Max Act: 0.8541. Min Act: -0.0000

Data Index: 1237104 (C4 (Web Text))

Max Activating Token Index: 264