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

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

Neuron 1916 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0952. Min Act: -0.0001

Data Index: 623798 (C4 (Web Text))

Max Activating Token Index: 149

Text #1

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0927. Min Act: -0.0001

Data Index: 318976 (C4 (Web Text))

Max Activating Token Index: 90

Text #2

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0865. Min Act: -0.0001

Data Index: 592178 (C4 (Web Text))

Max Activating Token Index: 643

Text #3

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0875. Min Act: -0.0001

Data Index: 894738 (C4 (Web Text))

Max Activating Token Index: 287

Text #4

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0789. Min Act: -0.0001

Data Index: 1170153 (C4 (Web Text))

Max Activating Token Index: 1006

Text #5

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0811. Min Act: -0.0001

Data Index: 3105 (C4 (Web Text))

Max Activating Token Index: 1010

Text #6

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0769. Min Act: -0.0001

Data Index: 1077268 (C4 (Web Text))

Max Activating Token Index: 155

Text #7

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0782. Min Act: -0.0001

Data Index: 1333546 (C4 (Web Text))

Max Activating Token Index: 384

Text #8

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0726. Min Act: -0.0001

Data Index: 278530 (C4 (Web Text))

Max Activating Token Index: 174

Text #9

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0728. Min Act: -0.0000

Data Index: 290291 (C4 (Web Text))

Max Activating Token Index: 116

Text #10

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0725. Min Act: -0.0001

Data Index: 1181387 (C4 (Web Text))

Max Activating Token Index: 300

Text #11

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0692. Min Act: -0.0001

Data Index: 178920 (C4 (Web Text))

Max Activating Token Index: 185

Text #12

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0659. Min Act: -0.0001

Data Index: 847396 (C4 (Web Text))

Max Activating Token Index: 536

Text #13

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0715. Min Act: -0.0001

Data Index: 936703 (C4 (Web Text))

Max Activating Token Index: 262

Text #14

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0706. Min Act: -0.0001

Data Index: 976707 (C4 (Web Text))

Max Activating Token Index: 923

Text #15

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0721. Min Act: -0.0001

Data Index: 668301 (C4 (Web Text))

Max Activating Token Index: 908

Text #16

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0689. Min Act: -0.0001

Data Index: 358047 (C4 (Web Text))

Max Activating Token Index: 181

Text #17

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0662. Min Act: -0.0001

Data Index: 596063 (C4 (Web Text))

Max Activating Token Index: 759

Text #18

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0651. Min Act: -0.0001

Data Index: 806400 (C4 (Web Text))

Max Activating Token Index: 746

Text #19

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0628. Min Act: -0.0001

Data Index: 1332406 (C4 (Web Text))

Max Activating Token Index: 740