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

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

Neuron 4962 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: 0.4863. Min Range: -0.4863

Max Act: 0.4863. Min Act: -0.0000

Data Index: 770676 (C4 (Web Text))

Max Activating Token Index: 911

Text #1

Max Range: 0.4863. Min Range: -0.4863

Max Act: 0.4587. Min Act: -0.0000

Data Index: 159453 (C4 (Web Text))

Max Activating Token Index: 323

Text #2

Max Range: 0.4863. Min Range: -0.4863

Max Act: 0.3993. Min Act: -0.0000

Data Index: 258517 (C4 (Web Text))

Max Activating Token Index: 769

Text #3

Max Range: 0.4863. Min Range: -0.4863

Max Act: 0.3869. Min Act: -0.0000

Data Index: 1182694 (C4 (Web Text))

Max Activating Token Index: 278

Text #4

Max Range: 0.4863. Min Range: -0.4863

Max Act: 0.3999. Min Act: -0.0000

Data Index: 449097 (C4 (Web Text))

Max Activating Token Index: 675

Text #5

Max Range: 0.4863. Min Range: -0.4863

Max Act: 0.4238. Min Act: -0.0000

Data Index: 1145695 (C4 (Web Text))

Max Activating Token Index: 184

Text #6

Max Range: 0.4863. Min Range: -0.4863

Max Act: 0.3799. Min Act: -0.0000

Data Index: 896496 (C4 (Web Text))

Max Activating Token Index: 262

Text #7

Max Range: 0.4863. Min Range: -0.4863

Max Act: 0.3884. Min Act: -0.0000

Data Index: 848063 (C4 (Web Text))

Max Activating Token Index: 794

Text #8

Max Range: 0.4863. Min Range: -0.4863

Max Act: 0.3849. Min Act: -0.0000

Data Index: 629361 (C4 (Web Text))

Max Activating Token Index: 594

Text #9

Max Range: 0.4863. Min Range: -0.4863

Max Act: 0.3815. Min Act: -0.0000

Data Index: 70369 (C4 (Web Text))

Max Activating Token Index: 1011

Text #10

Max Range: 0.4863. Min Range: -0.4863

Max Act: 0.3661. Min Act: -0.0000

Data Index: 596441 (C4 (Web Text))

Max Activating Token Index: 903

Text #11

Max Range: 0.4863. Min Range: -0.4863

Max Act: 0.3765. Min Act: -0.0000

Data Index: 787988 (C4 (Web Text))

Max Activating Token Index: 500

Text #12

Max Range: 0.4863. Min Range: -0.4863

Max Act: 0.3341. Min Act: -0.0000

Data Index: 567072 (C4 (Web Text))

Max Activating Token Index: 880

Text #13

Max Range: 0.4863. Min Range: -0.4863

Max Act: 0.3723. Min Act: -0.0000

Data Index: 829288 (C4 (Web Text))

Max Activating Token Index: 67

Text #14

Max Range: 0.4863. Min Range: -0.4863

Max Act: 0.3995. Min Act: -0.0000

Data Index: 823991 (C4 (Web Text))

Max Activating Token Index: 762

Text #15

Max Range: 0.4863. Min Range: -0.4863

Max Act: 0.3563. Min Act: 0.0000

Data Index: 135075 (C4 (Web Text))

Max Activating Token Index: 572

Text #16

Max Range: 0.4863. Min Range: -0.4863

Max Act: 0.3684. Min Act: -0.0000

Data Index: 1231608 (C4 (Web Text))

Max Activating Token Index: 414

Text #17

Max Range: 0.4863. Min Range: -0.4863

Max Act: 0.3640. Min Act: -0.0000

Data Index: 1150226 (C4 (Web Text))

Max Activating Token Index: 30

Text #18

Max Range: 0.4863. Min Range: -0.4863

Max Act: 0.3740. Min Act: -0.0000

Data Index: 1183700 (C4 (Web Text))

Max Activating Token Index: 699

Text #19

Max Range: 0.4863. Min Range: -0.4863

Max Act: 0.3603. Min Act: -0.0000

Data Index: 17117 (C4 (Web Text))

Max Activating Token Index: 61