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

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

Neuron 521 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1698. Min Range: -1.1698

Max Act: 1.1698. Min Act: -0.0001

Data Index: 1439454 (Python Code)

Max Activating Token Index: 881

Text #1

Max Range: 1.1698. Min Range: -1.1698

Max Act: 1.0390. Min Act: -0.0001

Data Index: 1394830 (Python Code)

Max Activating Token Index: 524

Text #2

Max Range: 1.1698. Min Range: -1.1698

Max Act: 1.0073. Min Act: -0.0001

Data Index: 1552116 (Python Code)

Max Activating Token Index: 397

Text #3

Max Range: 1.1698. Min Range: -1.1698

Max Act: 1.0214. Min Act: -0.0001

Data Index: 1602602 (Python Code)

Max Activating Token Index: 520

Text #4

Max Range: 1.1698. Min Range: -1.1698

Max Act: 1.0355. Min Act: -0.0001

Data Index: 1529269 (Python Code)

Max Activating Token Index: 494

Text #5

Max Range: 1.1698. Min Range: -1.1698

Max Act: 0.9408. Min Act: -0.0001

Data Index: 1461529 (Python Code)

Max Activating Token Index: 825

Text #6

Max Range: 1.1698. Min Range: -1.1698

Max Act: 1.0544. Min Act: -0.0001

Data Index: 1532429 (Python Code)

Max Activating Token Index: 987

Text #7

Max Range: 1.1698. Min Range: -1.1698

Max Act: 1.0529. Min Act: -0.0001

Data Index: 1390820 (Python Code)

Max Activating Token Index: 7

Text #8

Max Range: 1.1698. Min Range: -1.1698

Max Act: 1.0705. Min Act: -0.0001

Data Index: 1558726 (Python Code)

Max Activating Token Index: 93

Text #9

Max Range: 1.1698. Min Range: -1.1698

Max Act: 1.0201. Min Act: -0.0001

Data Index: 1491809 (Python Code)

Max Activating Token Index: 520

Text #10

Max Range: 1.1698. Min Range: -1.1698

Max Act: 0.9990. Min Act: -0.0001

Data Index: 1364574 (Python Code)

Max Activating Token Index: 38

Text #11

Max Range: 1.1698. Min Range: -1.1698

Max Act: 0.9721. Min Act: -0.0001

Data Index: 1645856 (Python Code)

Max Activating Token Index: 272

Text #12

Max Range: 1.1698. Min Range: -1.1698

Max Act: 0.8464. Min Act: -0.0001

Data Index: 1431205 (Python Code)

Max Activating Token Index: 292

Text #13

Max Range: 1.1698. Min Range: -1.1698

Max Act: 0.9114. Min Act: -0.0001

Data Index: 1516268 (Python Code)

Max Activating Token Index: 486

Text #14

Max Range: 1.1698. Min Range: -1.1698

Max Act: 0.9428. Min Act: -0.0001

Data Index: 1461782 (Python Code)

Max Activating Token Index: 1003

Text #15

Max Range: 1.1698. Min Range: -1.1698

Max Act: 1.1043. Min Act: -0.0001

Data Index: 1466018 (Python Code)

Max Activating Token Index: 857

Text #16

Max Range: 1.1698. Min Range: -1.1698

Max Act: 0.9931. Min Act: -0.0001

Data Index: 1643002 (Python Code)

Max Activating Token Index: 985

Text #17

Max Range: 1.1698. Min Range: -1.1698

Max Act: 0.9207. Min Act: -0.0001

Data Index: 1470965 (Python Code)

Max Activating Token Index: 996

Text #18

Max Range: 1.1698. Min Range: -1.1698

Max Act: 0.9427. Min Act: -0.0001

Data Index: 1563217 (Python Code)

Max Activating Token Index: 326

Text #19

Max Range: 1.1698. Min Range: -1.1698

Max Act: 0.9176. Min Act: -0.0001

Data Index: 1573502 (Python Code)

Max Activating Token Index: 338