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

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

Neuron 25 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0859. Min Act: -0.0000

Data Index: 146949 (C4 (Web Text))

Max Activating Token Index: 371

Text #1

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0990. Min Act: -0.0000

Data Index: 784150 (C4 (Web Text))

Max Activating Token Index: 500

Text #2

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0976. Min Act: -0.0000

Data Index: 685588 (C4 (Web Text))

Max Activating Token Index: 88

Text #3

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.1185. Min Act: -0.0000

Data Index: 757208 (C4 (Web Text))

Max Activating Token Index: 380

Text #4

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0970. Min Act: -0.0000

Data Index: 941008 (C4 (Web Text))

Max Activating Token Index: 84

Text #5

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0880. Min Act: -0.0000

Data Index: 335794 (C4 (Web Text))

Max Activating Token Index: 534

Text #6

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0737. Min Act: -0.0000

Data Index: 1106809 (C4 (Web Text))

Max Activating Token Index: 635

Text #7

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0719. Min Act: -0.0000

Data Index: 568877 (C4 (Web Text))

Max Activating Token Index: 818

Text #8

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0703. Min Act: -0.0000

Data Index: 31074 (C4 (Web Text))

Max Activating Token Index: 184

Text #9

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0691. Min Act: -0.0000

Data Index: 686725 (C4 (Web Text))

Max Activating Token Index: 565

Text #10

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0674. Min Act: -0.0001

Data Index: 190503 (C4 (Web Text))

Max Activating Token Index: 356

Text #11

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0659. Min Act: -0.0001

Data Index: 173031 (C4 (Web Text))

Max Activating Token Index: 418

Text #12

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0698. Min Act: -0.0000

Data Index: 1022078 (C4 (Web Text))

Max Activating Token Index: 1000

Text #13

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0650. Min Act: -0.0000

Data Index: 1108887 (C4 (Web Text))

Max Activating Token Index: 790

Text #14

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0654. Min Act: -0.0000

Data Index: 597639 (C4 (Web Text))

Max Activating Token Index: 126

Text #15

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0597. Min Act: -0.0000

Data Index: 221297 (C4 (Web Text))

Max Activating Token Index: 780

Text #16

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0548. Min Act: -0.0000

Data Index: 596899 (C4 (Web Text))

Max Activating Token Index: 332

Text #17

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0540. Min Act: -0.0000

Data Index: 149095 (C4 (Web Text))

Max Activating Token Index: 231

Text #18

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0527. Min Act: -0.0000

Data Index: 574123 (C4 (Web Text))

Max Activating Token Index: 667

Text #19

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0583. Min Act: -0.0000

Data Index: 413990 (C4 (Web Text))

Max Activating Token Index: 299