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

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

Neuron 5220 in Layer 1

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: 0.0952. Min Range: -0.0952

Max Act: 0.0952. Min Act: -0.0002

Data Index: 1224591 (C4 (Web Text))

Max Activating Token Index: 355

Text #1

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0945. Min Act: -0.0002

Data Index: 1351367 (C4 (Web Text))

Max Activating Token Index: 818

Text #2

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0905. Min Act: -0.0002

Data Index: 745970 (C4 (Web Text))

Max Activating Token Index: 57

Text #3

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0891. Min Act: -0.0002

Data Index: 964085 (C4 (Web Text))

Max Activating Token Index: 913

Text #4

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0870. Min Act: -0.0002

Data Index: 775663 (C4 (Web Text))

Max Activating Token Index: 857

Text #5

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0864. Min Act: -0.0002

Data Index: 14269 (C4 (Web Text))

Max Activating Token Index: 767

Text #6

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0838. Min Act: -0.0002

Data Index: 1060561 (C4 (Web Text))

Max Activating Token Index: 853

Text #7

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0812. Min Act: -0.0003

Data Index: 1298424 (C4 (Web Text))

Max Activating Token Index: 277

Text #8

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0798. Min Act: -0.0002

Data Index: 899439 (C4 (Web Text))

Max Activating Token Index: 289

Text #9

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0807. Min Act: -0.0002

Data Index: 658132 (C4 (Web Text))

Max Activating Token Index: 727

Text #10

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0814. Min Act: -0.0002

Data Index: 1284360 (C4 (Web Text))

Max Activating Token Index: 71

Text #11

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0798. Min Act: -0.0002

Data Index: 697010 (C4 (Web Text))

Max Activating Token Index: 45

Text #12

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0792. Min Act: -0.0003

Data Index: 628277 (C4 (Web Text))

Max Activating Token Index: 47

Text #13

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0801. Min Act: -0.0002

Data Index: 705306 (C4 (Web Text))

Max Activating Token Index: 125

Text #14

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0777. Min Act: -0.0002

Data Index: 1211495 (C4 (Web Text))

Max Activating Token Index: 518

Text #15

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0779. Min Act: -0.0002

Data Index: 364938 (C4 (Web Text))

Max Activating Token Index: 935

Text #16

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0774. Min Act: -0.0003

Data Index: 302089 (C4 (Web Text))

Max Activating Token Index: 115

Text #17

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0781. Min Act: -0.0003

Data Index: 1322090 (C4 (Web Text))

Max Activating Token Index: 196

Text #18

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0767. Min Act: -0.0002

Data Index: 1079007 (C4 (Web Text))

Max Activating Token Index: 199

Text #19

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0765. Min Act: -0.0002

Data Index: 398543 (C4 (Web Text))

Max Activating Token Index: 479