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

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

Neuron 3129 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: 0.9333. Min Range: -0.9333

Max Act: 0.9333. Min Act: -0.0001

Data Index: 761352 (C4 (Web Text))

Max Activating Token Index: 356

Text #1

Max Range: 0.9333. Min Range: -0.9333

Max Act: 0.7937. Min Act: -0.0001

Data Index: 1104357 (C4 (Web Text))

Max Activating Token Index: 316

Text #2

Max Range: 0.9333. Min Range: -0.9333

Max Act: 0.9138. Min Act: -0.0001

Data Index: 388314 (C4 (Web Text))

Max Activating Token Index: 492

Text #3

Max Range: 0.9333. Min Range: -0.9333

Max Act: 0.8983. Min Act: -0.0001

Data Index: 1038375 (C4 (Web Text))

Max Activating Token Index: 471

Text #4

Max Range: 0.9333. Min Range: -0.9333

Max Act: 0.8667. Min Act: -0.0001

Data Index: 747458 (C4 (Web Text))

Max Activating Token Index: 564

Text #5

Max Range: 0.9333. Min Range: -0.9333

Max Act: 0.8507. Min Act: -0.0001

Data Index: 880787 (C4 (Web Text))

Max Activating Token Index: 159

Text #6

Max Range: 0.9333. Min Range: -0.9333

Max Act: 0.8434. Min Act: -0.0001

Data Index: 1075621 (C4 (Web Text))

Max Activating Token Index: 99

Text #7

Max Range: 0.9333. Min Range: -0.9333

Max Act: 0.8075. Min Act: -0.0001

Data Index: 199513 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 0.9333. Min Range: -0.9333

Max Act: 0.8126. Min Act: -0.0001

Data Index: 982147 (C4 (Web Text))

Max Activating Token Index: 683

Text #9

Max Range: 0.9333. Min Range: -0.9333

Max Act: 0.8155. Min Act: -0.0001

Data Index: 174131 (C4 (Web Text))

Max Activating Token Index: 714

Text #10

Max Range: 0.9333. Min Range: -0.9333

Max Act: 0.7264. Min Act: -0.0001

Data Index: 519032 (C4 (Web Text))

Max Activating Token Index: 933

Text #11

Max Range: 0.9333. Min Range: -0.9333

Max Act: 0.8065. Min Act: -0.0001

Data Index: 1129108 (C4 (Web Text))

Max Activating Token Index: 179

Text #12

Max Range: 0.9333. Min Range: -0.9333

Max Act: 0.7351. Min Act: -0.0001

Data Index: 1135240 (C4 (Web Text))

Max Activating Token Index: 843

Text #13

Max Range: 0.9333. Min Range: -0.9333

Max Act: 0.8258. Min Act: -0.0001

Data Index: 375109 (C4 (Web Text))

Max Activating Token Index: 536

Text #14

Max Range: 0.9333. Min Range: -0.9333

Max Act: 0.7005. Min Act: -0.0001

Data Index: 1199301 (C4 (Web Text))

Max Activating Token Index: 192

Text #15

Max Range: 0.9333. Min Range: -0.9333

Max Act: 0.7942. Min Act: -0.0001

Data Index: 942794 (C4 (Web Text))

Max Activating Token Index: 350

Text #16

Max Range: 0.9333. Min Range: -0.9333

Max Act: 0.7207. Min Act: -0.0001

Data Index: 822846 (C4 (Web Text))

Max Activating Token Index: 896

Text #17

Max Range: 0.9333. Min Range: -0.9333

Max Act: 0.7233. Min Act: -0.0001

Data Index: 1345757 (C4 (Web Text))

Max Activating Token Index: 968

Text #18

Max Range: 0.9333. Min Range: -0.9333

Max Act: 0.7593. Min Act: -0.0001

Data Index: 1255137 (C4 (Web Text))

Max Activating Token Index: 710

Text #19

Max Range: 0.9333. Min Range: -0.9333

Max Act: 0.7894. Min Act: -0.0001

Data Index: 728721 (C4 (Web Text))

Max Activating Token Index: 496