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

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

Neuron 2682 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9287. Min Range: -0.9287

Max Act: 0.9287. Min Act: -0.0001

Data Index: 1456348 (Python Code)

Max Activating Token Index: 390

Text #1

Max Range: 0.9287. Min Range: -0.9287

Max Act: 0.7395. Min Act: -0.0001

Data Index: 1505145 (Python Code)

Max Activating Token Index: 779

Text #2

Max Range: 0.9287. Min Range: -0.9287

Max Act: 0.7788. Min Act: -0.0001

Data Index: 1470067 (Python Code)

Max Activating Token Index: 686

Text #3

Max Range: 0.9287. Min Range: -0.9287

Max Act: 0.7698. Min Act: -0.0001

Data Index: 1589845 (Python Code)

Max Activating Token Index: 278

Text #4

Max Range: 0.9287. Min Range: -0.9287

Max Act: 0.7092. Min Act: -0.0001

Data Index: 1506630 (Python Code)

Max Activating Token Index: 428

Text #5

Max Range: 0.9287. Min Range: -0.9287

Max Act: 0.7018. Min Act: -0.0001

Data Index: 1648665 (Python Code)

Max Activating Token Index: 169

Text #6

Max Range: 0.9287. Min Range: -0.9287

Max Act: 0.6891. Min Act: -0.0001

Data Index: 1538866 (Python Code)

Max Activating Token Index: 831

Text #7

Max Range: 0.9287. Min Range: -0.9287

Max Act: 0.6787. Min Act: -0.0001

Data Index: 1622708 (Python Code)

Max Activating Token Index: 989

Text #8

Max Range: 0.9287. Min Range: -0.9287

Max Act: 0.6586. Min Act: -0.0001

Data Index: 1493434 (Python Code)

Max Activating Token Index: 641

Text #9

Max Range: 0.9287. Min Range: -0.9287

Max Act: 0.6772. Min Act: -0.0001

Data Index: 1481305 (Python Code)

Max Activating Token Index: 749

Text #10

Max Range: 0.9287. Min Range: -0.9287

Max Act: 0.6310. Min Act: -0.0001

Data Index: 1507744 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.9287. Min Range: -0.9287

Max Act: 0.6469. Min Act: -0.0001

Data Index: 1643140 (Python Code)

Max Activating Token Index: 833

Text #12

Max Range: 0.9287. Min Range: -0.9287

Max Act: 0.6470. Min Act: -0.0001

Data Index: 1603725 (Python Code)

Max Activating Token Index: 309

Text #13

Max Range: 0.9287. Min Range: -0.9287

Max Act: 0.6275. Min Act: -0.0001

Data Index: 1655746 (Python Code)

Max Activating Token Index: 104

Text #14

Max Range: 0.9287. Min Range: -0.9287

Max Act: 0.6017. Min Act: -0.0001

Data Index: 1499889 (Python Code)

Max Activating Token Index: 388

Text #15

Max Range: 0.9287. Min Range: -0.9287

Max Act: 0.5892. Min Act: -0.0001

Data Index: 1634087 (Python Code)

Max Activating Token Index: 955

Text #16

Max Range: 0.9287. Min Range: -0.9287

Max Act: 0.6266. Min Act: -0.0001

Data Index: 1481990 (Python Code)

Max Activating Token Index: 954

Text #17

Max Range: 0.9287. Min Range: -0.9287

Max Act: 0.5893. Min Act: -0.0001

Data Index: 1581034 (Python Code)

Max Activating Token Index: 978

Text #18

Max Range: 0.9287. Min Range: -0.9287

Max Act: 0.6064. Min Act: -0.0001

Data Index: 1594561 (Python Code)

Max Activating Token Index: 437

Text #19

Max Range: 0.9287. Min Range: -0.9287

Max Act: 0.5849. Min Act: -0.0001

Data Index: 1444203 (Python Code)

Max Activating Token Index: 907