Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3551 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0798. Min Act: -0.0003

Data Index: 746989 (C4 (Web Text))

Max Activating Token Index: 348

Text #1

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0748. Min Act: -0.0004

Data Index: 889528 (C4 (Web Text))

Max Activating Token Index: 348

Text #2

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0715. Min Act: -0.0003

Data Index: 232262 (C4 (Web Text))

Max Activating Token Index: 930

Text #3

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0661. Min Act: -0.0003

Data Index: 344989 (C4 (Web Text))

Max Activating Token Index: 961

Text #4

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0698. Min Act: -0.0003

Data Index: 96229 (C4 (Web Text))

Max Activating Token Index: 541

Text #5

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0694. Min Act: -0.0003

Data Index: 104293 (C4 (Web Text))

Max Activating Token Index: 810

Text #6

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0692. Min Act: -0.0003

Data Index: 384251 (C4 (Web Text))

Max Activating Token Index: 486

Text #7

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0683. Min Act: -0.0003

Data Index: 727484 (C4 (Web Text))

Max Activating Token Index: 767

Text #8

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0671. Min Act: -0.0003

Data Index: 254477 (C4 (Web Text))

Max Activating Token Index: 124

Text #9

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0647. Min Act: -0.0003

Data Index: 544766 (C4 (Web Text))

Max Activating Token Index: 548

Text #10

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0694. Min Act: -0.0003

Data Index: 418929 (C4 (Web Text))

Max Activating Token Index: 312

Text #11

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0670. Min Act: -0.0003

Data Index: 1240211 (C4 (Web Text))

Max Activating Token Index: 948

Text #12

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0622. Min Act: -0.0003

Data Index: 859722 (C4 (Web Text))

Max Activating Token Index: 730

Text #13

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0641. Min Act: -0.0003

Data Index: 686919 (C4 (Web Text))

Max Activating Token Index: 226

Text #14

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0640. Min Act: -0.0003

Data Index: 516332 (C4 (Web Text))

Max Activating Token Index: 91

Text #15

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0686. Min Act: -0.0004

Data Index: 859728 (C4 (Web Text))

Max Activating Token Index: 821

Text #16

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0608. Min Act: -0.0004

Data Index: 108950 (C4 (Web Text))

Max Activating Token Index: 958

Text #17

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0630. Min Act: -0.0003

Data Index: 679722 (C4 (Web Text))

Max Activating Token Index: 487

Text #18

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0607. Min Act: -0.0003

Data Index: 818174 (C4 (Web Text))

Max Activating Token Index: 172

Text #19

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0627. Min Act: -0.0003

Data Index: 1196275 (C4 (Web Text))

Max Activating Token Index: 749