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

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

Neuron 1764 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2825. Min Range: -1.2825

Max Act: 1.2825. Min Act: -0.0001

Data Index: 1480195 (Python Code)

Max Activating Token Index: 747

Text #1

Max Range: 1.2825. Min Range: -1.2825

Max Act: 1.1415. Min Act: -0.0001

Data Index: 1557408 (Python Code)

Max Activating Token Index: 1013

Text #2

Max Range: 1.2825. Min Range: -1.2825

Max Act: 1.0249. Min Act: -0.0001

Data Index: 1482539 (Python Code)

Max Activating Token Index: 154

Text #3

Max Range: 1.2825. Min Range: -1.2825

Max Act: 0.9730. Min Act: -0.0001

Data Index: 1439456 (Python Code)

Max Activating Token Index: 1009

Text #4

Max Range: 1.2825. Min Range: -1.2825

Max Act: 0.9217. Min Act: -0.0001

Data Index: 1432575 (Python Code)

Max Activating Token Index: 992

Text #5

Max Range: 1.2825. Min Range: -1.2825

Max Act: 0.9008. Min Act: -0.0001

Data Index: 1410856 (Python Code)

Max Activating Token Index: 976

Text #6

Max Range: 1.2825. Min Range: -1.2825

Max Act: 0.8632. Min Act: -0.0000

Data Index: 1422829 (Python Code)

Max Activating Token Index: 738

Text #7

Max Range: 1.2825. Min Range: -1.2825

Max Act: 0.8403. Min Act: -0.0001

Data Index: 1568863 (Python Code)

Max Activating Token Index: 135

Text #8

Max Range: 1.2825. Min Range: -1.2825

Max Act: 0.8576. Min Act: -0.0001

Data Index: 1504231 (Python Code)

Max Activating Token Index: 833

Text #9

Max Range: 1.2825. Min Range: -1.2825

Max Act: 0.8349. Min Act: -0.0001

Data Index: 1451900 (Python Code)

Max Activating Token Index: 792

Text #10

Max Range: 1.2825. Min Range: -1.2825

Max Act: 0.8643. Min Act: -0.0001

Data Index: 1577295 (Python Code)

Max Activating Token Index: 537

Text #11

Max Range: 1.2825. Min Range: -1.2825

Max Act: 0.8326. Min Act: -0.0001

Data Index: 1519569 (Python Code)

Max Activating Token Index: 690

Text #12

Max Range: 1.2825. Min Range: -1.2825

Max Act: 0.8309. Min Act: -0.0001

Data Index: 1381688 (Python Code)

Max Activating Token Index: 284

Text #13

Max Range: 1.2825. Min Range: -1.2825

Max Act: 0.8249. Min Act: -0.0001

Data Index: 1419221 (Python Code)

Max Activating Token Index: 385

Text #14

Max Range: 1.2825. Min Range: -1.2825

Max Act: 0.8758. Min Act: -0.0001

Data Index: 1545356 (Python Code)

Max Activating Token Index: 122

Text #15

Max Range: 1.2825. Min Range: -1.2825

Max Act: 0.8104. Min Act: -0.0001

Data Index: 1541132 (Python Code)

Max Activating Token Index: 840

Text #16

Max Range: 1.2825. Min Range: -1.2825

Max Act: 0.8306. Min Act: -0.0001

Data Index: 1466526 (Python Code)

Max Activating Token Index: 572

Text #17

Max Range: 1.2825. Min Range: -1.2825

Max Act: 0.8066. Min Act: -0.0001

Data Index: 1524110 (Python Code)

Max Activating Token Index: 757

Text #18

Max Range: 1.2825. Min Range: -1.2825

Max Act: 0.8587. Min Act: -0.0001

Data Index: 1624129 (Python Code)

Max Activating Token Index: 970

Text #19

Max Range: 1.2825. Min Range: -1.2825

Max Act: 0.7762. Min Act: -0.0001

Data Index: 1532032 (Python Code)

Max Activating Token Index: 219