Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1855 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.3334. Min Range: -2.3334

Max Act: 2.3334. Min Act: -0.0000

Data Index: 1411677 (Python Code)

Max Activating Token Index: 28

Text #1

Max Range: 2.3334. Min Range: -2.3334

Max Act: 2.1158. Min Act: -0.0000

Data Index: 1522788 (Python Code)

Max Activating Token Index: 922

Text #2

Max Range: 2.3334. Min Range: -2.3334

Max Act: 2.0136. Min Act: -0.0000

Data Index: 1656418 (Python Code)

Max Activating Token Index: 374

Text #3

Max Range: 2.3334. Min Range: -2.3334

Max Act: 1.8576. Min Act: -0.0000

Data Index: 1447278 (Python Code)

Max Activating Token Index: 706

Text #4

Max Range: 2.3334. Min Range: -2.3334

Max Act: 1.7460. Min Act: -0.0000

Data Index: 1603832 (Python Code)

Max Activating Token Index: 688

Text #5

Max Range: 2.3334. Min Range: -2.3334

Max Act: 1.7843. Min Act: -0.0000

Data Index: 1452189 (Python Code)

Max Activating Token Index: 903

Text #6

Max Range: 2.3334. Min Range: -2.3334

Max Act: 1.8216. Min Act: -0.0000

Data Index: 1388465 (Python Code)

Max Activating Token Index: 524

Text #7

Max Range: 2.3334. Min Range: -2.3334

Max Act: 1.7068. Min Act: -0.0000

Data Index: 1379544 (Python Code)

Max Activating Token Index: 493

Text #8

Max Range: 2.3334. Min Range: -2.3334

Max Act: 1.9548. Min Act: -0.0000

Data Index: 1625530 (Python Code)

Max Activating Token Index: 281

Text #9

Max Range: 2.3334. Min Range: -2.3334

Max Act: 1.8419. Min Act: -0.0000

Data Index: 1521120 (Python Code)

Max Activating Token Index: 939

Text #10

Max Range: 2.3334. Min Range: -2.3334

Max Act: 1.8169. Min Act: -0.0000

Data Index: 1578593 (Python Code)

Max Activating Token Index: 964

Text #11

Max Range: 2.3334. Min Range: -2.3334

Max Act: 1.7337. Min Act: -0.0000

Data Index: 1499113 (Python Code)

Max Activating Token Index: 862

Text #12

Max Range: 2.3334. Min Range: -2.3334

Max Act: 1.7998. Min Act: -0.0000

Data Index: 1604338 (Python Code)

Max Activating Token Index: 705

Text #13

Max Range: 2.3334. Min Range: -2.3334

Max Act: 1.7586. Min Act: -0.0000

Data Index: 1632781 (Python Code)

Max Activating Token Index: 205

Text #14

Max Range: 2.3334. Min Range: -2.3334

Max Act: 1.6781. Min Act: -0.0000

Data Index: 1473598 (Python Code)

Max Activating Token Index: 699

Text #15

Max Range: 2.3334. Min Range: -2.3334

Max Act: 1.7558. Min Act: -0.0000

Data Index: 1628150 (Python Code)

Max Activating Token Index: 714

Text #16

Max Range: 2.3334. Min Range: -2.3334

Max Act: 1.7093. Min Act: -0.0000

Data Index: 1544163 (Python Code)

Max Activating Token Index: 529

Text #17

Max Range: 2.3334. Min Range: -2.3334

Max Act: 1.7097. Min Act: -0.0000

Data Index: 1365067 (Python Code)

Max Activating Token Index: 507

Text #18

Max Range: 2.3334. Min Range: -2.3334

Max Act: 1.7135. Min Act: -0.0000

Data Index: 1554590 (Python Code)

Max Activating Token Index: 317

Text #19

Max Range: 2.3334. Min Range: -2.3334

Max Act: 1.7597. Min Act: -0.0000

Data Index: 1464768 (Python Code)

Max Activating Token Index: 32