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

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

Neuron 1836 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.2342. Min Act: -0.0001

Data Index: 835155 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1965. Min Act: -0.0001

Data Index: 1084962 (C4 (Web Text))

Max Activating Token Index: 351

Text #2

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1917. Min Act: -0.0001

Data Index: 1315778 (C4 (Web Text))

Max Activating Token Index: 893

Text #3

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1616. Min Act: -0.0001

Data Index: 1149790 (C4 (Web Text))

Max Activating Token Index: 599

Text #4

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1739. Min Act: -0.0001

Data Index: 574155 (C4 (Web Text))

Max Activating Token Index: 140

Text #5

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1771. Min Act: -0.0001

Data Index: 45608 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1687. Min Act: -0.0001

Data Index: 660552 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1738. Min Act: -0.0001

Data Index: 1324652 (C4 (Web Text))

Max Activating Token Index: 223

Text #8

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1539. Min Act: -0.0001

Data Index: 843639 (C4 (Web Text))

Max Activating Token Index: 13

Text #9

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1538. Min Act: -0.0001

Data Index: 1022956 (C4 (Web Text))

Max Activating Token Index: 282

Text #10

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1558. Min Act: -0.0001

Data Index: 757443 (C4 (Web Text))

Max Activating Token Index: 572

Text #11

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1537. Min Act: -0.0001

Data Index: 295174 (C4 (Web Text))

Max Activating Token Index: 340

Text #12

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1563. Min Act: -0.0001

Data Index: 1144117 (C4 (Web Text))

Max Activating Token Index: 387

Text #13

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1521. Min Act: -0.0001

Data Index: 320202 (C4 (Web Text))

Max Activating Token Index: 830

Text #14

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1383. Min Act: -0.0001

Data Index: 394385 (C4 (Web Text))

Max Activating Token Index: 168

Text #15

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1374. Min Act: -0.0001

Data Index: 869341 (C4 (Web Text))

Max Activating Token Index: 376

Text #16

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1398. Min Act: -0.0001

Data Index: 141222 (C4 (Web Text))

Max Activating Token Index: 183

Text #17

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1388. Min Act: -0.0001

Data Index: 100851 (C4 (Web Text))

Max Activating Token Index: 598

Text #18

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1519. Min Act: -0.0001

Data Index: 30306 (C4 (Web Text))

Max Activating Token Index: 703

Text #19

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1402. Min Act: -0.0001

Data Index: 983168 (C4 (Web Text))

Max Activating Token Index: 347