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

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

Neuron 293 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7445. Min Range: -4.7445

Max Act: 4.7445. Min Act: -0.0000

Data Index: 1150766 (C4 (Web Text))

Max Activating Token Index: 601

Text #1

Max Range: 4.7445. Min Range: -4.7445

Max Act: 4.0631. Min Act: -0.0000

Data Index: 1124283 (C4 (Web Text))

Max Activating Token Index: 299

Text #2

Max Range: 4.7445. Min Range: -4.7445

Max Act: 4.2290. Min Act: -0.0000

Data Index: 32979 (C4 (Web Text))

Max Activating Token Index: 391

Text #3

Max Range: 4.7445. Min Range: -4.7445

Max Act: 4.4059. Min Act: -0.0000

Data Index: 567683 (C4 (Web Text))

Max Activating Token Index: 439

Text #4

Max Range: 4.7445. Min Range: -4.7445

Max Act: 4.0390. Min Act: -0.0000

Data Index: 22238 (C4 (Web Text))

Max Activating Token Index: 756

Text #5

Max Range: 4.7445. Min Range: -4.7445

Max Act: 4.1482. Min Act: -0.0000

Data Index: 367052 (C4 (Web Text))

Max Activating Token Index: 758

Text #6

Max Range: 4.7445. Min Range: -4.7445

Max Act: 3.9067. Min Act: -0.0000

Data Index: 616015 (C4 (Web Text))

Max Activating Token Index: 596

Text #7

Max Range: 4.7445. Min Range: -4.7445

Max Act: 4.0013. Min Act: -0.0000

Data Index: 860306 (C4 (Web Text))

Max Activating Token Index: 248

Text #8

Max Range: 4.7445. Min Range: -4.7445

Max Act: 4.0234. Min Act: -0.0000

Data Index: 886234 (C4 (Web Text))

Max Activating Token Index: 857

Text #9

Max Range: 4.7445. Min Range: -4.7445

Max Act: 3.9635. Min Act: -0.0000

Data Index: 104667 (C4 (Web Text))

Max Activating Token Index: 893

Text #10

Max Range: 4.7445. Min Range: -4.7445

Max Act: 3.9237. Min Act: -0.0000

Data Index: 641945 (C4 (Web Text))

Max Activating Token Index: 345

Text #11

Max Range: 4.7445. Min Range: -4.7445

Max Act: 3.9155. Min Act: -0.0000

Data Index: 224356 (C4 (Web Text))

Max Activating Token Index: 424

Text #12

Max Range: 4.7445. Min Range: -4.7445

Max Act: 3.9216. Min Act: -0.0000

Data Index: 102401 (C4 (Web Text))

Max Activating Token Index: 554

Text #13

Max Range: 4.7445. Min Range: -4.7445

Max Act: 4.0627. Min Act: -0.0000

Data Index: 1316541 (C4 (Web Text))

Max Activating Token Index: 312

Text #14

Max Range: 4.7445. Min Range: -4.7445

Max Act: 3.7285. Min Act: -0.0000

Data Index: 1193113 (C4 (Web Text))

Max Activating Token Index: 702

Text #15

Max Range: 4.7445. Min Range: -4.7445

Max Act: 3.9710. Min Act: -0.0000

Data Index: 944495 (C4 (Web Text))

Max Activating Token Index: 940

Text #16

Max Range: 4.7445. Min Range: -4.7445

Max Act: 3.6138. Min Act: -0.0000

Data Index: 220157 (C4 (Web Text))

Max Activating Token Index: 823

Text #17

Max Range: 4.7445. Min Range: -4.7445

Max Act: 3.5752. Min Act: -0.0000

Data Index: 1335404 (C4 (Web Text))

Max Activating Token Index: 733

Text #18

Max Range: 4.7445. Min Range: -4.7445

Max Act: 3.5832. Min Act: -0.0000

Data Index: 823293 (C4 (Web Text))

Max Activating Token Index: 754

Text #19

Max Range: 4.7445. Min Range: -4.7445

Max Act: 3.7695. Min Act: -0.0000

Data Index: 1206288 (C4 (Web Text))

Max Activating Token Index: 699