Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1508 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.6021. Min Range: -0.6021

Max Act: 0.6021. Min Act: -0.0006

Data Index: 888102 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 0.6021. Min Range: -0.6021

Max Act: 0.5292. Min Act: -0.0006

Data Index: 1641725 (Python Code)

Max Activating Token Index: 2

Text #2

Max Range: 0.6021. Min Range: -0.6021

Max Act: 0.3948. Min Act: -0.0006

Data Index: 1364252 (Python Code)

Max Activating Token Index: 75

Text #3

Max Range: 0.6021. Min Range: -0.6021

Max Act: 0.3681. Min Act: -0.0006

Data Index: 1358095 (C4 (Web Text))

Max Activating Token Index: 176

Text #4

Max Range: 0.6021. Min Range: -0.6021

Max Act: 0.2858. Min Act: -0.0006

Data Index: 1445175 (Python Code)

Max Activating Token Index: 6

Text #5

Max Range: 0.6021. Min Range: -0.6021

Max Act: 0.3155. Min Act: -0.0006

Data Index: 556002 (C4 (Web Text))

Max Activating Token Index: 368

Text #6

Max Range: 0.6021. Min Range: -0.6021

Max Act: 0.3068. Min Act: -0.0006

Data Index: 1379339 (Python Code)

Max Activating Token Index: 71

Text #7

Max Range: 0.6021. Min Range: -0.6021

Max Act: 0.2848. Min Act: -0.0006

Data Index: 1510593 (Python Code)

Max Activating Token Index: 63

Text #8

Max Range: 0.6021. Min Range: -0.6021

Max Act: 0.2732. Min Act: -0.0006

Data Index: 1435282 (Python Code)

Max Activating Token Index: 335

Text #9

Max Range: 0.6021. Min Range: -0.6021

Max Act: 0.2662. Min Act: -0.0006

Data Index: 557620 (C4 (Web Text))

Max Activating Token Index: 98

Text #10

Max Range: 0.6021. Min Range: -0.6021

Max Act: 0.2441. Min Act: -0.0006

Data Index: 919090 (C4 (Web Text))

Max Activating Token Index: 952

Text #11

Max Range: 0.6021. Min Range: -0.6021

Max Act: 0.2643. Min Act: -0.0006

Data Index: 1098961 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 0.6021. Min Range: -0.6021

Max Act: 0.2440. Min Act: -0.0006

Data Index: 1470177 (Python Code)

Max Activating Token Index: 187

Text #13

Max Range: 0.6021. Min Range: -0.6021

Max Act: 0.2547. Min Act: -0.0006

Data Index: 1362852 (Python Code)

Max Activating Token Index: 1

Text #14

Max Range: 0.6021. Min Range: -0.6021

Max Act: 0.2528. Min Act: -0.0006

Data Index: 1578655 (Python Code)

Max Activating Token Index: 307

Text #15

Max Range: 0.6021. Min Range: -0.6021

Max Act: 0.2182. Min Act: -0.0006

Data Index: 679817 (C4 (Web Text))

Max Activating Token Index: 186

Text #16

Max Range: 0.6021. Min Range: -0.6021

Max Act: 0.2398. Min Act: -0.0006

Data Index: 1565578 (Python Code)

Max Activating Token Index: 21

Text #17

Max Range: 0.6021. Min Range: -0.6021

Max Act: 0.2167. Min Act: -0.0006

Data Index: 1539160 (Python Code)

Max Activating Token Index: 75

Text #18

Max Range: 0.6021. Min Range: -0.6021

Max Act: 0.2065. Min Act: -0.0005

Data Index: 1533839 (Python Code)

Max Activating Token Index: 125

Text #19

Max Range: 0.6021. Min Range: -0.6021

Max Act: 0.1920. Min Act: -0.0006

Data Index: 1481823 (Python Code)

Max Activating Token Index: 540