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

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

Neuron 3781 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: 0.1106. Min Range: -0.1106

Max Act: 0.1106. Min Act: -0.0001

Data Index: 453491 (C4 (Web Text))

Max Activating Token Index: 642

Text #1

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0989. Min Act: -0.0001

Data Index: 1039465 (C4 (Web Text))

Max Activating Token Index: 918

Text #2

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0916. Min Act: -0.0001

Data Index: 430376 (C4 (Web Text))

Max Activating Token Index: 157

Text #3

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0735. Min Act: -0.0001

Data Index: 950029 (C4 (Web Text))

Max Activating Token Index: 489

Text #4

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0792. Min Act: -0.0001

Data Index: 259488 (C4 (Web Text))

Max Activating Token Index: 827

Text #5

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0764. Min Act: -0.0001

Data Index: 991751 (C4 (Web Text))

Max Activating Token Index: 34

Text #6

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0752. Min Act: -0.0001

Data Index: 844512 (C4 (Web Text))

Max Activating Token Index: 429

Text #7

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0811. Min Act: -0.0001

Data Index: 1107077 (C4 (Web Text))

Max Activating Token Index: 943

Text #8

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0799. Min Act: -0.0001

Data Index: 527890 (C4 (Web Text))

Max Activating Token Index: 581

Text #9

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0657. Min Act: -0.0001

Data Index: 1265997 (C4 (Web Text))

Max Activating Token Index: 143

Text #10

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0735. Min Act: -0.0001

Data Index: 828751 (C4 (Web Text))

Max Activating Token Index: 567

Text #11

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0766. Min Act: -0.0001

Data Index: 604506 (C4 (Web Text))

Max Activating Token Index: 984

Text #12

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0735. Min Act: -0.0001

Data Index: 1249688 (C4 (Web Text))

Max Activating Token Index: 714

Text #13

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0728. Min Act: -0.0001

Data Index: 1156989 (C4 (Web Text))

Max Activating Token Index: 1000

Text #14

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0740. Min Act: -0.0001

Data Index: 205127 (C4 (Web Text))

Max Activating Token Index: 800

Text #15

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0739. Min Act: -0.0001

Data Index: 798987 (C4 (Web Text))

Max Activating Token Index: 953

Text #16

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0716. Min Act: -0.0001

Data Index: 18046 (C4 (Web Text))

Max Activating Token Index: 128

Text #17

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0689. Min Act: -0.0001

Data Index: 710951 (C4 (Web Text))

Max Activating Token Index: 365

Text #18

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0665. Min Act: -0.0001

Data Index: 1337524 (C4 (Web Text))

Max Activating Token Index: 542

Text #19

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0704. Min Act: -0.0001

Data Index: 466631 (C4 (Web Text))

Max Activating Token Index: 433