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

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

Neuron 4982 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: 0.1029. Min Range: -0.1029

Max Act: 0.1029. Min Act: -0.0002

Data Index: 315779 (C4 (Web Text))

Max Activating Token Index: 75

Text #1

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.1012. Min Act: -0.0002

Data Index: 526917 (C4 (Web Text))

Max Activating Token Index: 913

Text #2

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0995. Min Act: -0.0002

Data Index: 176737 (C4 (Web Text))

Max Activating Token Index: 19

Text #3

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0990. Min Act: -0.0002

Data Index: 1206236 (C4 (Web Text))

Max Activating Token Index: 916

Text #4

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0906. Min Act: -0.0002

Data Index: 346097 (C4 (Web Text))

Max Activating Token Index: 944

Text #5

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0894. Min Act: -0.0002

Data Index: 156506 (C4 (Web Text))

Max Activating Token Index: 895

Text #6

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0884. Min Act: -0.0002

Data Index: 1098193 (C4 (Web Text))

Max Activating Token Index: 889

Text #7

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0877. Min Act: -0.0002

Data Index: 127216 (C4 (Web Text))

Max Activating Token Index: 482

Text #8

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0886. Min Act: -0.0002

Data Index: 804138 (C4 (Web Text))

Max Activating Token Index: 155

Text #9

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0875. Min Act: -0.0002

Data Index: 981977 (C4 (Web Text))

Max Activating Token Index: 99

Text #10

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0876. Min Act: -0.0002

Data Index: 455691 (C4 (Web Text))

Max Activating Token Index: 678

Text #11

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0880. Min Act: -0.0002

Data Index: 716078 (C4 (Web Text))

Max Activating Token Index: 572

Text #12

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0863. Min Act: -0.0002

Data Index: 1128322 (C4 (Web Text))

Max Activating Token Index: 539

Text #13

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0837. Min Act: -0.0002

Data Index: 560297 (C4 (Web Text))

Max Activating Token Index: 640

Text #14

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0863. Min Act: -0.0002

Data Index: 818826 (C4 (Web Text))

Max Activating Token Index: 997

Text #15

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0827. Min Act: -0.0002

Data Index: 935804 (C4 (Web Text))

Max Activating Token Index: 360

Text #16

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0836. Min Act: -0.0002

Data Index: 344180 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0821. Min Act: -0.0002

Data Index: 265885 (C4 (Web Text))

Max Activating Token Index: 610

Text #18

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0819. Min Act: -0.0002

Data Index: 382681 (C4 (Web Text))

Max Activating Token Index: 354

Text #19

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0839. Min Act: -0.0002

Data Index: 672513 (C4 (Web Text))

Max Activating Token Index: 5