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

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

Neuron 1756 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5762. Min Range: -4.5762

Max Act: 4.5762. Min Act: -0.0000

Data Index: 1508994 (Python Code)

Max Activating Token Index: 859

Text #1

Max Range: 4.5762. Min Range: -4.5762

Max Act: 3.3959. Min Act: -0.0000

Data Index: 1652248 (Python Code)

Max Activating Token Index: 560

Text #2

Max Range: 4.5762. Min Range: -4.5762

Max Act: 3.3928. Min Act: -0.0000

Data Index: 1486894 (Python Code)

Max Activating Token Index: 485

Text #3

Max Range: 4.5762. Min Range: -4.5762

Max Act: 2.8741. Min Act: -0.0000

Data Index: 1445306 (Python Code)

Max Activating Token Index: 392

Text #4

Max Range: 4.5762. Min Range: -4.5762

Max Act: 3.0255. Min Act: -0.0000

Data Index: 1562465 (Python Code)

Max Activating Token Index: 672

Text #5

Max Range: 4.5762. Min Range: -4.5762

Max Act: 2.7085. Min Act: -0.0000

Data Index: 1388687 (Python Code)

Max Activating Token Index: 781

Text #6

Max Range: 4.5762. Min Range: -4.5762

Max Act: 2.7009. Min Act: -0.0000

Data Index: 1398779 (Python Code)

Max Activating Token Index: 903

Text #7

Max Range: 4.5762. Min Range: -4.5762

Max Act: 2.8369. Min Act: -0.0000

Data Index: 1484859 (Python Code)

Max Activating Token Index: 102

Text #8

Max Range: 4.5762. Min Range: -4.5762

Max Act: 2.8127. Min Act: -0.0000

Data Index: 1370178 (Python Code)

Max Activating Token Index: 423

Text #9

Max Range: 4.5762. Min Range: -4.5762

Max Act: 2.6803. Min Act: -0.0000

Data Index: 1528706 (Python Code)

Max Activating Token Index: 884

Text #10

Max Range: 4.5762. Min Range: -4.5762

Max Act: 2.8524. Min Act: -0.0000

Data Index: 1378183 (Python Code)

Max Activating Token Index: 537

Text #11

Max Range: 4.5762. Min Range: -4.5762

Max Act: 2.5998. Min Act: -0.0000

Data Index: 1431471 (Python Code)

Max Activating Token Index: 152

Text #12

Max Range: 4.5762. Min Range: -4.5762

Max Act: 2.5842. Min Act: -0.0000

Data Index: 1402050 (Python Code)

Max Activating Token Index: 92

Text #13

Max Range: 4.5762. Min Range: -4.5762

Max Act: 2.5654. Min Act: -0.0000

Data Index: 1487604 (Python Code)

Max Activating Token Index: 411

Text #14

Max Range: 4.5762. Min Range: -4.5762

Max Act: 2.5129. Min Act: -0.0000

Data Index: 1565375 (Python Code)

Max Activating Token Index: 851

Text #15

Max Range: 4.5762. Min Range: -4.5762

Max Act: 2.5171. Min Act: -0.0000

Data Index: 1386358 (Python Code)

Max Activating Token Index: 319

Text #16

Max Range: 4.5762. Min Range: -4.5762

Max Act: 2.5252. Min Act: -0.0000

Data Index: 1502426 (Python Code)

Max Activating Token Index: 212

Text #17

Max Range: 4.5762. Min Range: -4.5762

Max Act: 2.7507. Min Act: -0.0000

Data Index: 1504225 (Python Code)

Max Activating Token Index: 173

Text #18

Max Range: 4.5762. Min Range: -4.5762

Max Act: 2.5106. Min Act: -0.0001

Data Index: 1642182 (Python Code)

Max Activating Token Index: 477

Text #19

Max Range: 4.5762. Min Range: -4.5762

Max Act: 2.4823. Min Act: -0.0000

Data Index: 1492993 (Python Code)

Max Activating Token Index: 1001