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

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

Neuron 5533 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.1153. Min Act: -0.0000

Data Index: 1084769 (C4 (Web Text))

Max Activating Token Index: 531

Text #1

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.1066. Min Act: -0.0000

Data Index: 867892 (C4 (Web Text))

Max Activating Token Index: 728

Text #2

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.1112. Min Act: -0.0000

Data Index: 795498 (C4 (Web Text))

Max Activating Token Index: 918

Text #3

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0986. Min Act: -0.0000

Data Index: 432226 (C4 (Web Text))

Max Activating Token Index: 163

Text #4

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0998. Min Act: -0.0000

Data Index: 1052699 (C4 (Web Text))

Max Activating Token Index: 569

Text #5

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0917. Min Act: -0.0000

Data Index: 330445 (C4 (Web Text))

Max Activating Token Index: 57

Text #6

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0910. Min Act: -0.0000

Data Index: 52657 (C4 (Web Text))

Max Activating Token Index: 921

Text #7

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0802. Min Act: -0.0000

Data Index: 338561 (C4 (Web Text))

Max Activating Token Index: 1015

Text #8

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0826. Min Act: -0.0000

Data Index: 1132529 (C4 (Web Text))

Max Activating Token Index: 254

Text #9

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0825. Min Act: -0.0000

Data Index: 344071 (C4 (Web Text))

Max Activating Token Index: 196

Text #10

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0821. Min Act: -0.0000

Data Index: 1013095 (C4 (Web Text))

Max Activating Token Index: 278

Text #11

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0768. Min Act: -0.0000

Data Index: 1288300 (C4 (Web Text))

Max Activating Token Index: 569

Text #12

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0811. Min Act: -0.0000

Data Index: 260073 (C4 (Web Text))

Max Activating Token Index: 969

Text #13

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0822. Min Act: -0.0000

Data Index: 1316091 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0758. Min Act: -0.0000

Data Index: 809561 (C4 (Web Text))

Max Activating Token Index: 364

Text #15

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0760. Min Act: -0.0000

Data Index: 737123 (C4 (Web Text))

Max Activating Token Index: 709

Text #16

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0823. Min Act: -0.0000

Data Index: 576271 (C4 (Web Text))

Max Activating Token Index: 903

Text #17

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0783. Min Act: -0.0000

Data Index: 1117322 (C4 (Web Text))

Max Activating Token Index: 999

Text #18

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0749. Min Act: -0.0000

Data Index: 343225 (C4 (Web Text))

Max Activating Token Index: 847

Text #19

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0771. Min Act: -0.0000

Data Index: 1236569 (C4 (Web Text))

Max Activating Token Index: 966