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

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

Neuron 1661 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: 0.3109. Min Range: -0.3109

Max Act: 0.3109. Min Act: -0.0000

Data Index: 955883 (C4 (Web Text))

Max Activating Token Index: 587

Text #1

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2831. Min Act: -0.0001

Data Index: 1625774 (Python Code)

Max Activating Token Index: 172

Text #2

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2753. Min Act: -0.0001

Data Index: 1634152 (Python Code)

Max Activating Token Index: 1021

Text #3

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2617. Min Act: -0.0001

Data Index: 1546992 (Python Code)

Max Activating Token Index: 802

Text #4

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2589. Min Act: -0.0001

Data Index: 1396202 (Python Code)

Max Activating Token Index: 854

Text #5

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2586. Min Act: -0.0000

Data Index: 1639260 (Python Code)

Max Activating Token Index: 969

Text #6

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2409. Min Act: -0.0000

Data Index: 1400385 (Python Code)

Max Activating Token Index: 9

Text #7

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2469. Min Act: -0.0000

Data Index: 1373524 (Python Code)

Max Activating Token Index: 60

Text #8

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2359. Min Act: -0.0000

Data Index: 1515965 (Python Code)

Max Activating Token Index: 851

Text #9

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2419. Min Act: -0.0000

Data Index: 1396109 (Python Code)

Max Activating Token Index: 39

Text #10

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2416. Min Act: -0.0001

Data Index: 1398838 (Python Code)

Max Activating Token Index: 968

Text #11

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2421. Min Act: -0.0000

Data Index: 1601055 (Python Code)

Max Activating Token Index: 301

Text #12

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2322. Min Act: -0.0001

Data Index: 1479723 (Python Code)

Max Activating Token Index: 116

Text #13

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2378. Min Act: -0.0000

Data Index: 253611 (C4 (Web Text))

Max Activating Token Index: 893

Text #14

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2187. Min Act: -0.0001

Data Index: 1381072 (Python Code)

Max Activating Token Index: 894

Text #15

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2241. Min Act: -0.0001

Data Index: 1436601 (Python Code)

Max Activating Token Index: 289

Text #16

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2294. Min Act: -0.0001

Data Index: 1613956 (Python Code)

Max Activating Token Index: 496

Text #17

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2205. Min Act: -0.0001

Data Index: 1384526 (Python Code)

Max Activating Token Index: 832

Text #18

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2129. Min Act: -0.0001

Data Index: 1467556 (Python Code)

Max Activating Token Index: 846

Text #19

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2097. Min Act: -0.0001

Data Index: 1387283 (Python Code)

Max Activating Token Index: 911