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

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

Neuron 467 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: 1.0001. Min Range: -1.0001

Max Act: 1.0001. Min Act: -0.0001

Data Index: 865313 (C4 (Web Text))

Max Activating Token Index: 956

Text #1

Max Range: 1.0001. Min Range: -1.0001

Max Act: 0.8486. Min Act: -0.0000

Data Index: 1394024 (Python Code)

Max Activating Token Index: 508

Text #2

Max Range: 1.0001. Min Range: -1.0001

Max Act: 0.9032. Min Act: -0.0001

Data Index: 976520 (C4 (Web Text))

Max Activating Token Index: 946

Text #3

Max Range: 1.0001. Min Range: -1.0001

Max Act: 0.8701. Min Act: -0.0001

Data Index: 834228 (C4 (Web Text))

Max Activating Token Index: 742

Text #4

Max Range: 1.0001. Min Range: -1.0001

Max Act: 0.8913. Min Act: -0.0001

Data Index: 606109 (C4 (Web Text))

Max Activating Token Index: 835

Text #5

Max Range: 1.0001. Min Range: -1.0001

Max Act: 0.8878. Min Act: -0.0001

Data Index: 745531 (C4 (Web Text))

Max Activating Token Index: 979

Text #6

Max Range: 1.0001. Min Range: -1.0001

Max Act: 0.6184. Min Act: -0.0000

Data Index: 1501210 (Python Code)

Max Activating Token Index: 736

Text #7

Max Range: 1.0001. Min Range: -1.0001

Max Act: 0.7400. Min Act: -0.0001

Data Index: 760406 (C4 (Web Text))

Max Activating Token Index: 714

Text #8

Max Range: 1.0001. Min Range: -1.0001

Max Act: 0.8085. Min Act: -0.0001

Data Index: 1218864 (C4 (Web Text))

Max Activating Token Index: 621

Text #9

Max Range: 1.0001. Min Range: -1.0001

Max Act: 0.8287. Min Act: -0.0000

Data Index: 1639010 (Python Code)

Max Activating Token Index: 191

Text #10

Max Range: 1.0001. Min Range: -1.0001

Max Act: 0.7994. Min Act: -0.0001

Data Index: 121006 (C4 (Web Text))

Max Activating Token Index: 477

Text #11

Max Range: 1.0001. Min Range: -1.0001

Max Act: 0.7206. Min Act: -0.0001

Data Index: 316288 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 1.0001. Min Range: -1.0001

Max Act: 0.7541. Min Act: -0.0001

Data Index: 373274 (C4 (Web Text))

Max Activating Token Index: 742

Text #13

Max Range: 1.0001. Min Range: -1.0001

Max Act: 0.7963. Min Act: -0.0001

Data Index: 1079804 (C4 (Web Text))

Max Activating Token Index: 1019

Text #14

Max Range: 1.0001. Min Range: -1.0001

Max Act: 0.8196. Min Act: -0.0001

Data Index: 1057022 (C4 (Web Text))

Max Activating Token Index: 915

Text #15

Max Range: 1.0001. Min Range: -1.0001

Max Act: 0.6651. Min Act: -0.0001

Data Index: 47114 (C4 (Web Text))

Max Activating Token Index: 572

Text #16

Max Range: 1.0001. Min Range: -1.0001

Max Act: 0.7580. Min Act: -0.0001

Data Index: 199200 (C4 (Web Text))

Max Activating Token Index: 510

Text #17

Max Range: 1.0001. Min Range: -1.0001

Max Act: 0.7358. Min Act: -0.0001

Data Index: 250027 (C4 (Web Text))

Max Activating Token Index: 732

Text #18

Max Range: 1.0001. Min Range: -1.0001

Max Act: 0.7609. Min Act: -0.0001

Data Index: 1267230 (C4 (Web Text))

Max Activating Token Index: 278

Text #19

Max Range: 1.0001. Min Range: -1.0001

Max Act: 0.7539. Min Act: -0.0001

Data Index: 832330 (C4 (Web Text))

Max Activating Token Index: 72