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

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

Neuron 1245 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4008. Min Range: -1.4008

Max Act: 1.4008. Min Act: -0.0001

Data Index: 144784 (C4 (Web Text))

Max Activating Token Index: 130

Text #1

Max Range: 1.4008. Min Range: -1.4008

Max Act: 1.3113. Min Act: -0.0001

Data Index: 564798 (C4 (Web Text))

Max Activating Token Index: 161

Text #2

Max Range: 1.4008. Min Range: -1.4008

Max Act: 1.2946. Min Act: -0.0001

Data Index: 542751 (C4 (Web Text))

Max Activating Token Index: 218

Text #3

Max Range: 1.4008. Min Range: -1.4008

Max Act: 1.2071. Min Act: -0.0001

Data Index: 614752 (C4 (Web Text))

Max Activating Token Index: 220

Text #4

Max Range: 1.4008. Min Range: -1.4008

Max Act: 1.2353. Min Act: -0.0001

Data Index: 1325784 (C4 (Web Text))

Max Activating Token Index: 251

Text #5

Max Range: 1.4008. Min Range: -1.4008

Max Act: 1.1944. Min Act: -0.0001

Data Index: 1303244 (C4 (Web Text))

Max Activating Token Index: 84

Text #6

Max Range: 1.4008. Min Range: -1.4008

Max Act: 1.0300. Min Act: -0.0001

Data Index: 624041 (C4 (Web Text))

Max Activating Token Index: 855

Text #7

Max Range: 1.4008. Min Range: -1.4008

Max Act: 0.8873. Min Act: -0.0001

Data Index: 1113295 (C4 (Web Text))

Max Activating Token Index: 861

Text #8

Max Range: 1.4008. Min Range: -1.4008

Max Act: 0.9679. Min Act: -0.0001

Data Index: 1432179 (Python Code)

Max Activating Token Index: 659

Text #9

Max Range: 1.4008. Min Range: -1.4008

Max Act: 0.9341. Min Act: -0.0001

Data Index: 429378 (C4 (Web Text))

Max Activating Token Index: 241

Text #10

Max Range: 1.4008. Min Range: -1.4008

Max Act: 0.8902. Min Act: -0.0001

Data Index: 812535 (C4 (Web Text))

Max Activating Token Index: 694

Text #11

Max Range: 1.4008. Min Range: -1.4008

Max Act: 0.8913. Min Act: -0.0001

Data Index: 618563 (C4 (Web Text))

Max Activating Token Index: 111

Text #12

Max Range: 1.4008. Min Range: -1.4008

Max Act: 0.8517. Min Act: -0.0001

Data Index: 1317736 (C4 (Web Text))

Max Activating Token Index: 980

Text #13

Max Range: 1.4008. Min Range: -1.4008

Max Act: 0.8430. Min Act: -0.0001

Data Index: 1163516 (C4 (Web Text))

Max Activating Token Index: 833

Text #14

Max Range: 1.4008. Min Range: -1.4008

Max Act: 0.8637. Min Act: -0.0001

Data Index: 1584249 (Python Code)

Max Activating Token Index: 731

Text #15

Max Range: 1.4008. Min Range: -1.4008

Max Act: 0.8450. Min Act: -0.0001

Data Index: 678361 (C4 (Web Text))

Max Activating Token Index: 551

Text #16

Max Range: 1.4008. Min Range: -1.4008

Max Act: 0.7293. Min Act: -0.0001

Data Index: 480403 (C4 (Web Text))

Max Activating Token Index: 949

Text #17

Max Range: 1.4008. Min Range: -1.4008

Max Act: 0.8181. Min Act: -0.0001

Data Index: 464361 (C4 (Web Text))

Max Activating Token Index: 990

Text #18

Max Range: 1.4008. Min Range: -1.4008

Max Act: 0.7347. Min Act: -0.0001

Data Index: 67865 (C4 (Web Text))

Max Activating Token Index: 805

Text #19

Max Range: 1.4008. Min Range: -1.4008

Max Act: 0.8642. Min Act: -0.0001

Data Index: 415261 (C4 (Web Text))

Max Activating Token Index: 874