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

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

Neuron 1433 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0944. Min Act: -0.0001

Data Index: 1610856 (Python Code)

Max Activating Token Index: 221

Text #1

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.1073. Min Act: -0.0001

Data Index: 1361797 (Python Code)

Max Activating Token Index: 13

Text #2

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.1019. Min Act: -0.0001

Data Index: 1466534 (Python Code)

Max Activating Token Index: 860

Text #3

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.1040. Min Act: -0.0001

Data Index: 1631628 (Python Code)

Max Activating Token Index: 102

Text #4

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0933. Min Act: -0.0001

Data Index: 1586755 (Python Code)

Max Activating Token Index: 340

Text #5

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0934. Min Act: -0.0001

Data Index: 1415912 (Python Code)

Max Activating Token Index: 185

Text #6

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0901. Min Act: -0.0001

Data Index: 1393415 (Python Code)

Max Activating Token Index: 743

Text #7

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0944. Min Act: -0.0001

Data Index: 1467300 (Python Code)

Max Activating Token Index: 96

Text #8

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0929. Min Act: -0.0001

Data Index: 1547119 (Python Code)

Max Activating Token Index: 71

Text #9

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0880. Min Act: -0.0001

Data Index: 1520284 (Python Code)

Max Activating Token Index: 642

Text #10

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0897. Min Act: -0.0001

Data Index: 1596022 (Python Code)

Max Activating Token Index: 20

Text #11

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0839. Min Act: -0.0001

Data Index: 1440171 (Python Code)

Max Activating Token Index: 60

Text #12

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0883. Min Act: -0.0001

Data Index: 1631498 (Python Code)

Max Activating Token Index: 494

Text #13

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0793. Min Act: -0.0001

Data Index: 1648002 (Python Code)

Max Activating Token Index: 73

Text #14

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0853. Min Act: -0.0001

Data Index: 1651289 (Python Code)

Max Activating Token Index: 240

Text #15

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0832. Min Act: -0.0001

Data Index: 1411896 (Python Code)

Max Activating Token Index: 60

Text #16

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0816. Min Act: -0.0001

Data Index: 1633436 (Python Code)

Max Activating Token Index: 295

Text #17

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0791. Min Act: -0.0001

Data Index: 1543979 (Python Code)

Max Activating Token Index: 901

Text #18

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0845. Min Act: -0.0001

Data Index: 1533484 (Python Code)

Max Activating Token Index: 386

Text #19

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0861. Min Act: -0.0001

Data Index: 1400762 (Python Code)

Max Activating Token Index: 30