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

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

Neuron 867 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0785. Min Act: -0.0002

Data Index: 786950 (C4 (Web Text))

Max Activating Token Index: 111

Text #1

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0750. Min Act: -0.0001

Data Index: 381623 (C4 (Web Text))

Max Activating Token Index: 232

Text #2

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0693. Min Act: -0.0001

Data Index: 57255 (C4 (Web Text))

Max Activating Token Index: 972

Text #3

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0682. Min Act: -0.0001

Data Index: 1118996 (C4 (Web Text))

Max Activating Token Index: 876

Text #4

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0677. Min Act: -0.0001

Data Index: 205624 (C4 (Web Text))

Max Activating Token Index: 491

Text #5

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0653. Min Act: -0.0001

Data Index: 266770 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0662. Min Act: -0.0001

Data Index: 701574 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0650. Min Act: -0.0001

Data Index: 300615 (C4 (Web Text))

Max Activating Token Index: 139

Text #8

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0650. Min Act: -0.0001

Data Index: 924882 (C4 (Web Text))

Max Activating Token Index: 103

Text #9

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0646. Min Act: -0.0001

Data Index: 737125 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0636. Min Act: -0.0001

Data Index: 602673 (C4 (Web Text))

Max Activating Token Index: 432

Text #11

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0641. Min Act: -0.0001

Data Index: 151004 (C4 (Web Text))

Max Activating Token Index: 719

Text #12

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0644. Min Act: -0.0001

Data Index: 1219703 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0636. Min Act: -0.0001

Data Index: 1122453 (C4 (Web Text))

Max Activating Token Index: 186

Text #14

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0640. Min Act: -0.0001

Data Index: 441509 (C4 (Web Text))

Max Activating Token Index: 230

Text #15

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0644. Min Act: -0.0001

Data Index: 611896 (C4 (Web Text))

Max Activating Token Index: 190

Text #16

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0626. Min Act: -0.0001

Data Index: 1044543 (C4 (Web Text))

Max Activating Token Index: 31

Text #17

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0630. Min Act: -0.0001

Data Index: 400685 (C4 (Web Text))

Max Activating Token Index: 649

Text #18

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0630. Min Act: -0.0001

Data Index: 263011 (C4 (Web Text))

Max Activating Token Index: 318

Text #19

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0622. Min Act: -0.0001

Data Index: 421009 (C4 (Web Text))

Max Activating Token Index: 41