Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3448 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.7133. Min Range: -1.7133

Max Act: 1.7133. Min Act: -0.0000

Data Index: 1255460 (C4 (Web Text))

Max Activating Token Index: 821

Text #1

Max Range: 1.7133. Min Range: -1.7133

Max Act: 1.6046. Min Act: -0.0000

Data Index: 527199 (C4 (Web Text))

Max Activating Token Index: 85

Text #2

Max Range: 1.7133. Min Range: -1.7133

Max Act: 1.4873. Min Act: -0.0000

Data Index: 1147843 (C4 (Web Text))

Max Activating Token Index: 969

Text #3

Max Range: 1.7133. Min Range: -1.7133

Max Act: 1.4879. Min Act: -0.0000

Data Index: 1123928 (C4 (Web Text))

Max Activating Token Index: 310

Text #4

Max Range: 1.7133. Min Range: -1.7133

Max Act: 1.6536. Min Act: -0.0000

Data Index: 1016639 (C4 (Web Text))

Max Activating Token Index: 961

Text #5

Max Range: 1.7133. Min Range: -1.7133

Max Act: 1.3862. Min Act: -0.0000

Data Index: 945994 (C4 (Web Text))

Max Activating Token Index: 31

Text #6

Max Range: 1.7133. Min Range: -1.7133

Max Act: 1.2653. Min Act: -0.0000

Data Index: 767966 (C4 (Web Text))

Max Activating Token Index: 237

Text #7

Max Range: 1.7133. Min Range: -1.7133

Max Act: 1.2896. Min Act: -0.0000

Data Index: 431764 (C4 (Web Text))

Max Activating Token Index: 821

Text #8

Max Range: 1.7133. Min Range: -1.7133

Max Act: 1.2733. Min Act: -0.0000

Data Index: 1178918 (C4 (Web Text))

Max Activating Token Index: 640

Text #9

Max Range: 1.7133. Min Range: -1.7133

Max Act: 1.2361. Min Act: -0.0000

Data Index: 87028 (C4 (Web Text))

Max Activating Token Index: 106

Text #10

Max Range: 1.7133. Min Range: -1.7133

Max Act: 1.1705. Min Act: -0.0000

Data Index: 102672 (C4 (Web Text))

Max Activating Token Index: 325

Text #11

Max Range: 1.7133. Min Range: -1.7133

Max Act: 1.1461. Min Act: -0.0000

Data Index: 576809 (C4 (Web Text))

Max Activating Token Index: 247

Text #12

Max Range: 1.7133. Min Range: -1.7133

Max Act: 1.1229. Min Act: -0.0000

Data Index: 341618 (C4 (Web Text))

Max Activating Token Index: 123

Text #13

Max Range: 1.7133. Min Range: -1.7133

Max Act: 1.1057. Min Act: -0.0000

Data Index: 1105221 (C4 (Web Text))

Max Activating Token Index: 794

Text #14

Max Range: 1.7133. Min Range: -1.7133

Max Act: 1.1885. Min Act: -0.0000

Data Index: 825016 (C4 (Web Text))

Max Activating Token Index: 28

Text #15

Max Range: 1.7133. Min Range: -1.7133

Max Act: 1.1779. Min Act: -0.0000

Data Index: 390004 (C4 (Web Text))

Max Activating Token Index: 162

Text #16

Max Range: 1.7133. Min Range: -1.7133

Max Act: 1.1071. Min Act: -0.0000

Data Index: 257089 (C4 (Web Text))

Max Activating Token Index: 945

Text #17

Max Range: 1.7133. Min Range: -1.7133

Max Act: 1.1731. Min Act: -0.0000

Data Index: 876354 (C4 (Web Text))

Max Activating Token Index: 49

Text #18

Max Range: 1.7133. Min Range: -1.7133

Max Act: 1.1526. Min Act: -0.0000

Data Index: 571070 (C4 (Web Text))

Max Activating Token Index: 122

Text #19

Max Range: 1.7133. Min Range: -1.7133

Max Act: 1.1273. Min Act: -0.0000

Data Index: 330451 (C4 (Web Text))

Max Activating Token Index: 91