Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5547 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7068. Min Range: -0.7068

Max Act: 0.6135. Min Act: -0.0000

Data Index: 279792 (C4 (Web Text))

Max Activating Token Index: 879

Text #1

Max Range: 0.7068. Min Range: -0.7068

Max Act: 0.6686. Min Act: -0.0000

Data Index: 376872 (C4 (Web Text))

Max Activating Token Index: 551

Text #2

Max Range: 0.7068. Min Range: -0.7068

Max Act: 0.7068. Min Act: -0.0000

Data Index: 659601 (C4 (Web Text))

Max Activating Token Index: 857

Text #3

Max Range: 0.7068. Min Range: -0.7068

Max Act: 0.5816. Min Act: -0.0000

Data Index: 1068436 (C4 (Web Text))

Max Activating Token Index: 832

Text #4

Max Range: 0.7068. Min Range: -0.7068

Max Act: 0.6752. Min Act: -0.0000

Data Index: 694629 (C4 (Web Text))

Max Activating Token Index: 384

Text #5

Max Range: 0.7068. Min Range: -0.7068

Max Act: 0.6243. Min Act: -0.0000

Data Index: 1030291 (C4 (Web Text))

Max Activating Token Index: 756

Text #6

Max Range: 0.7068. Min Range: -0.7068

Max Act: 0.6798. Min Act: -0.0000

Data Index: 339170 (C4 (Web Text))

Max Activating Token Index: 483

Text #7

Max Range: 0.7068. Min Range: -0.7068

Max Act: 0.5943. Min Act: -0.0000

Data Index: 103809 (C4 (Web Text))

Max Activating Token Index: 917

Text #8

Max Range: 0.7068. Min Range: -0.7068

Max Act: 0.5524. Min Act: -0.0000

Data Index: 303680 (C4 (Web Text))

Max Activating Token Index: 18

Text #9

Max Range: 0.7068. Min Range: -0.7068

Max Act: 0.5362. Min Act: -0.0000

Data Index: 701986 (C4 (Web Text))

Max Activating Token Index: 367

Text #10

Max Range: 0.7068. Min Range: -0.7068

Max Act: 0.6178. Min Act: -0.0000

Data Index: 487748 (C4 (Web Text))

Max Activating Token Index: 857

Text #11

Max Range: 0.7068. Min Range: -0.7068

Max Act: 0.5230. Min Act: -0.0000

Data Index: 406990 (C4 (Web Text))

Max Activating Token Index: 354

Text #12

Max Range: 0.7068. Min Range: -0.7068

Max Act: 0.5100. Min Act: -0.0000

Data Index: 961293 (C4 (Web Text))

Max Activating Token Index: 240

Text #13

Max Range: 0.7068. Min Range: -0.7068

Max Act: 0.4901. Min Act: -0.0000

Data Index: 1055034 (C4 (Web Text))

Max Activating Token Index: 185

Text #14

Max Range: 0.7068. Min Range: -0.7068

Max Act: 0.6004. Min Act: -0.0000

Data Index: 369619 (C4 (Web Text))

Max Activating Token Index: 928

Text #15

Max Range: 0.7068. Min Range: -0.7068

Max Act: 0.4885. Min Act: -0.0000

Data Index: 1084069 (C4 (Web Text))

Max Activating Token Index: 935

Text #16

Max Range: 0.7068. Min Range: -0.7068

Max Act: 0.5031. Min Act: -0.0000

Data Index: 1285548 (C4 (Web Text))

Max Activating Token Index: 501

Text #17

Max Range: 0.7068. Min Range: -0.7068

Max Act: 0.5113. Min Act: -0.0000

Data Index: 768342 (C4 (Web Text))

Max Activating Token Index: 96

Text #18

Max Range: 0.7068. Min Range: -0.7068

Max Act: 0.5133. Min Act: -0.0000

Data Index: 336012 (C4 (Web Text))

Max Activating Token Index: 735

Text #19

Max Range: 0.7068. Min Range: -0.7068

Max Act: 0.4954. Min Act: -0.0000

Data Index: 684770 (C4 (Web Text))

Max Activating Token Index: 140