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

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

Neuron 576 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: 0.1009. Min Range: -0.1009

Max Act: 0.0989. Min Act: -0.0004

Data Index: 1139361 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.1009. Min Act: -0.0004

Data Index: 454369 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0972. Min Act: -0.0004

Data Index: 197299 (C4 (Web Text))

Max Activating Token Index: 47

Text #3

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0931. Min Act: -0.0004

Data Index: 371832 (C4 (Web Text))

Max Activating Token Index: 44

Text #4

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0954. Min Act: -0.0004

Data Index: 224741 (C4 (Web Text))

Max Activating Token Index: 16

Text #5

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0894. Min Act: -0.0004

Data Index: 579927 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0926. Min Act: -0.0004

Data Index: 802347 (C4 (Web Text))

Max Activating Token Index: 55

Text #7

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0925. Min Act: -0.0004

Data Index: 660615 (C4 (Web Text))

Max Activating Token Index: 129

Text #8

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0924. Min Act: -0.0004

Data Index: 756945 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0958. Min Act: -0.0004

Data Index: 485083 (C4 (Web Text))

Max Activating Token Index: 309

Text #10

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0913. Min Act: -0.0004

Data Index: 330334 (C4 (Web Text))

Max Activating Token Index: 405

Text #11

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0877. Min Act: -0.0004

Data Index: 1330628 (C4 (Web Text))

Max Activating Token Index: 25

Text #12

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0864. Min Act: -0.0004

Data Index: 1125000 (C4 (Web Text))

Max Activating Token Index: 17

Text #13

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0889. Min Act: -0.0004

Data Index: 567065 (C4 (Web Text))

Max Activating Token Index: 39

Text #14

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0853. Min Act: -0.0004

Data Index: 180052 (C4 (Web Text))

Max Activating Token Index: 85

Text #15

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0885. Min Act: -0.0004

Data Index: 1288559 (C4 (Web Text))

Max Activating Token Index: 77

Text #16

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0881. Min Act: -0.0004

Data Index: 501976 (C4 (Web Text))

Max Activating Token Index: 401

Text #17

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0840. Min Act: -0.0004

Data Index: 674616 (C4 (Web Text))

Max Activating Token Index: 262

Text #18

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0906. Min Act: -0.0004

Data Index: 749730 (C4 (Web Text))

Max Activating Token Index: 315

Text #19

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0836. Min Act: -0.0004

Data Index: 348235 (C4 (Web Text))

Max Activating Token Index: 355