Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2752 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0940. Min Act: -0.0004

Data Index: 175131 (C4 (Web Text))

Max Activating Token Index: 269

Text #1

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0874. Min Act: -0.0004

Data Index: 614183 (C4 (Web Text))

Max Activating Token Index: 161

Text #2

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0910. Min Act: -0.0004

Data Index: 1357888 (C4 (Web Text))

Max Activating Token Index: 814

Text #3

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0865. Min Act: -0.0004

Data Index: 1256908 (C4 (Web Text))

Max Activating Token Index: 916

Text #4

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0896. Min Act: -0.0004

Data Index: 234010 (C4 (Web Text))

Max Activating Token Index: 78

Text #5

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0883. Min Act: -0.0004

Data Index: 224656 (C4 (Web Text))

Max Activating Token Index: 957

Text #6

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0796. Min Act: -0.0004

Data Index: 173101 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0886. Min Act: -0.0004

Data Index: 291961 (C4 (Web Text))

Max Activating Token Index: 76

Text #8

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0842. Min Act: -0.0004

Data Index: 94342 (C4 (Web Text))

Max Activating Token Index: 379

Text #9

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0777. Min Act: -0.0004

Data Index: 661894 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0771. Min Act: -0.0004

Data Index: 1150240 (C4 (Web Text))

Max Activating Token Index: 424

Text #11

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0783. Min Act: -0.0004

Data Index: 410186 (C4 (Web Text))

Max Activating Token Index: 87

Text #12

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0836. Min Act: -0.0004

Data Index: 473400 (C4 (Web Text))

Max Activating Token Index: 37

Text #13

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0746. Min Act: -0.0004

Data Index: 1137320 (C4 (Web Text))

Max Activating Token Index: 1017

Text #14

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0769. Min Act: -0.0004

Data Index: 136343 (C4 (Web Text))

Max Activating Token Index: 404

Text #15

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0796. Min Act: -0.0004

Data Index: 1460898 (Python Code)

Max Activating Token Index: 1007

Text #16

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0764. Min Act: -0.0004

Data Index: 95051 (C4 (Web Text))

Max Activating Token Index: 483

Text #17

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0737. Min Act: -0.0004

Data Index: 1254612 (C4 (Web Text))

Max Activating Token Index: 802

Text #18

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0731. Min Act: -0.0004

Data Index: 9243 (C4 (Web Text))

Max Activating Token Index: 300

Text #19

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0787. Min Act: -0.0004

Data Index: 147005 (C4 (Web Text))

Max Activating Token Index: 1017