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

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

Neuron 2676 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: 5.2800. Min Range: -5.2800

Max Act: 5.2800. Min Act: -0.0000

Data Index: 531263 (C4 (Web Text))

Max Activating Token Index: 942

Text #1

Max Range: 5.2800. Min Range: -5.2800

Max Act: 4.8800. Min Act: -0.0000

Data Index: 77997 (C4 (Web Text))

Max Activating Token Index: 721

Text #2

Max Range: 5.2800. Min Range: -5.2800

Max Act: 5.0047. Min Act: -0.0000

Data Index: 930788 (C4 (Web Text))

Max Activating Token Index: 671

Text #3

Max Range: 5.2800. Min Range: -5.2800

Max Act: 3.5470. Min Act: -0.0000

Data Index: 954947 (C4 (Web Text))

Max Activating Token Index: 625

Text #4

Max Range: 5.2800. Min Range: -5.2800

Max Act: 3.3382. Min Act: -0.0000

Data Index: 698616 (C4 (Web Text))

Max Activating Token Index: 1020

Text #5

Max Range: 5.2800. Min Range: -5.2800

Max Act: 3.2962. Min Act: -0.0000

Data Index: 1146721 (C4 (Web Text))

Max Activating Token Index: 834

Text #6

Max Range: 5.2800. Min Range: -5.2800

Max Act: 3.2801. Min Act: -0.0000

Data Index: 1371975 (Python Code)

Max Activating Token Index: 1012

Text #7

Max Range: 5.2800. Min Range: -5.2800

Max Act: 3.2723. Min Act: -0.0000

Data Index: 1362682 (Python Code)

Max Activating Token Index: 692

Text #8

Max Range: 5.2800. Min Range: -5.2800

Max Act: 3.1866. Min Act: -0.0000

Data Index: 1325137 (C4 (Web Text))

Max Activating Token Index: 58

Text #9

Max Range: 5.2800. Min Range: -5.2800

Max Act: 3.0740. Min Act: -0.0000

Data Index: 99263 (C4 (Web Text))

Max Activating Token Index: 851

Text #10

Max Range: 5.2800. Min Range: -5.2800

Max Act: 3.0138. Min Act: -0.0000

Data Index: 345554 (C4 (Web Text))

Max Activating Token Index: 744

Text #11

Max Range: 5.2800. Min Range: -5.2800

Max Act: 3.0027. Min Act: -0.0000

Data Index: 563042 (C4 (Web Text))

Max Activating Token Index: 614

Text #12

Max Range: 5.2800. Min Range: -5.2800

Max Act: 2.9552. Min Act: -0.0000

Data Index: 1540948 (Python Code)

Max Activating Token Index: 730

Text #13

Max Range: 5.2800. Min Range: -5.2800

Max Act: 2.9522. Min Act: -0.0000

Data Index: 553778 (C4 (Web Text))

Max Activating Token Index: 605

Text #14

Max Range: 5.2800. Min Range: -5.2800

Max Act: 2.9408. Min Act: -0.0000

Data Index: 1510787 (Python Code)

Max Activating Token Index: 185

Text #15

Max Range: 5.2800. Min Range: -5.2800

Max Act: 2.9215. Min Act: -0.0000

Data Index: 1033347 (C4 (Web Text))

Max Activating Token Index: 45

Text #16

Max Range: 5.2800. Min Range: -5.2800

Max Act: 3.1845. Min Act: -0.0000

Data Index: 1304415 (C4 (Web Text))

Max Activating Token Index: 168

Text #17

Max Range: 5.2800. Min Range: -5.2800

Max Act: 2.8632. Min Act: -0.0000

Data Index: 1553096 (Python Code)

Max Activating Token Index: 790

Text #18

Max Range: 5.2800. Min Range: -5.2800

Max Act: 2.7263. Min Act: -0.0000

Data Index: 1309833 (C4 (Web Text))

Max Activating Token Index: 289

Text #19

Max Range: 5.2800. Min Range: -5.2800

Max Act: 2.8557. Min Act: -0.0000

Data Index: 537027 (C4 (Web Text))

Max Activating Token Index: 481