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

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

Neuron 3072 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.1063. Min Act: -0.0002

Data Index: 270061 (C4 (Web Text))

Max Activating Token Index: 317

Text #1

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.1015. Min Act: -0.0002

Data Index: 789112 (C4 (Web Text))

Max Activating Token Index: 493

Text #2

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0968. Min Act: -0.0002

Data Index: 53787 (C4 (Web Text))

Max Activating Token Index: 527

Text #3

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0950. Min Act: -0.0002

Data Index: 741588 (C4 (Web Text))

Max Activating Token Index: 218

Text #4

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0916. Min Act: -0.0002

Data Index: 901164 (C4 (Web Text))

Max Activating Token Index: 558

Text #5

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0895. Min Act: -0.0002

Data Index: 104991 (C4 (Web Text))

Max Activating Token Index: 413

Text #6

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0893. Min Act: -0.0002

Data Index: 1176281 (C4 (Web Text))

Max Activating Token Index: 178

Text #7

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0882. Min Act: -0.0002

Data Index: 916999 (C4 (Web Text))

Max Activating Token Index: 383

Text #8

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0838. Min Act: -0.0002

Data Index: 943669 (C4 (Web Text))

Max Activating Token Index: 61

Text #9

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0839. Min Act: -0.0002

Data Index: 467915 (C4 (Web Text))

Max Activating Token Index: 106

Text #10

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0827. Min Act: -0.0002

Data Index: 880432 (C4 (Web Text))

Max Activating Token Index: 618

Text #11

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0810. Min Act: -0.0002

Data Index: 897595 (C4 (Web Text))

Max Activating Token Index: 425

Text #12

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0805. Min Act: -0.0002

Data Index: 800565 (C4 (Web Text))

Max Activating Token Index: 80

Text #13

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0822. Min Act: -0.0002

Data Index: 769004 (C4 (Web Text))

Max Activating Token Index: 726

Text #14

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0801. Min Act: -0.0002

Data Index: 324978 (C4 (Web Text))

Max Activating Token Index: 873

Text #15

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0763. Min Act: -0.0002

Data Index: 144738 (C4 (Web Text))

Max Activating Token Index: 531

Text #16

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0755. Min Act: -0.0002

Data Index: 1018895 (C4 (Web Text))

Max Activating Token Index: 683

Text #17

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0789. Min Act: -0.0002

Data Index: 408161 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0781. Min Act: -0.0002

Data Index: 456082 (C4 (Web Text))

Max Activating Token Index: 573

Text #19

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0742. Min Act: -0.0002

Data Index: 863257 (C4 (Web Text))

Max Activating Token Index: 93