Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3366 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.1142. Min Act: -0.0001

Data Index: 1094051 (C4 (Web Text))

Max Activating Token Index: 783

Text #1

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.1019. Min Act: -0.0001

Data Index: 934617 (C4 (Web Text))

Max Activating Token Index: 573

Text #2

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0981. Min Act: -0.0001

Data Index: 1067794 (C4 (Web Text))

Max Activating Token Index: 755

Text #3

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0961. Min Act: -0.0001

Data Index: 227035 (C4 (Web Text))

Max Activating Token Index: 960

Text #4

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0932. Min Act: -0.0001

Data Index: 753812 (C4 (Web Text))

Max Activating Token Index: 506

Text #5

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0881. Min Act: -0.0001

Data Index: 366573 (C4 (Web Text))

Max Activating Token Index: 982

Text #6

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0967. Min Act: -0.0001

Data Index: 622175 (C4 (Web Text))

Max Activating Token Index: 889

Text #7

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0953. Min Act: -0.0001

Data Index: 83957 (C4 (Web Text))

Max Activating Token Index: 29

Text #8

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0910. Min Act: -0.0001

Data Index: 213000 (C4 (Web Text))

Max Activating Token Index: 772

Text #9

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0898. Min Act: -0.0001

Data Index: 1264350 (C4 (Web Text))

Max Activating Token Index: 795

Text #10

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0902. Min Act: -0.0001

Data Index: 1275053 (C4 (Web Text))

Max Activating Token Index: 758

Text #11

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0845. Min Act: -0.0001

Data Index: 400295 (C4 (Web Text))

Max Activating Token Index: 232

Text #12

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0838. Min Act: -0.0001

Data Index: 678309 (C4 (Web Text))

Max Activating Token Index: 71

Text #13

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0777. Min Act: -0.0001

Data Index: 944286 (C4 (Web Text))

Max Activating Token Index: 688

Text #14

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0831. Min Act: -0.0001

Data Index: 667334 (C4 (Web Text))

Max Activating Token Index: 16

Text #15

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0917. Min Act: -0.0001

Data Index: 675176 (C4 (Web Text))

Max Activating Token Index: 650

Text #16

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0782. Min Act: -0.0001

Data Index: 201477 (C4 (Web Text))

Max Activating Token Index: 889

Text #17

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0885. Min Act: -0.0001

Data Index: 1098964 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0821. Min Act: -0.0001

Data Index: 958233 (C4 (Web Text))

Max Activating Token Index: 875

Text #19

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0789. Min Act: -0.0001

Data Index: 1251580 (C4 (Web Text))

Max Activating Token Index: 433