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

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

Neuron 4987 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4107. Min Range: -2.4107

Max Act: 2.3154. Min Act: -0.0002

Data Index: 827712 (C4 (Web Text))

Max Activating Token Index: 183

Text #1

Max Range: 2.4107. Min Range: -2.4107

Max Act: 2.4107. Min Act: -0.0002

Data Index: 589319 (C4 (Web Text))

Max Activating Token Index: 470

Text #2

Max Range: 2.4107. Min Range: -2.4107

Max Act: 2.2702. Min Act: -0.0002

Data Index: 724415 (C4 (Web Text))

Max Activating Token Index: 620

Text #3

Max Range: 2.4107. Min Range: -2.4107

Max Act: 2.3675. Min Act: -0.0002

Data Index: 150121 (C4 (Web Text))

Max Activating Token Index: 169

Text #4

Max Range: 2.4107. Min Range: -2.4107

Max Act: 2.4089. Min Act: -0.0002

Data Index: 277075 (C4 (Web Text))

Max Activating Token Index: 766

Text #5

Max Range: 2.4107. Min Range: -2.4107

Max Act: 2.1838. Min Act: -0.0002

Data Index: 270705 (C4 (Web Text))

Max Activating Token Index: 143

Text #6

Max Range: 2.4107. Min Range: -2.4107

Max Act: 1.9826. Min Act: -0.0002

Data Index: 473571 (C4 (Web Text))

Max Activating Token Index: 342

Text #7

Max Range: 2.4107. Min Range: -2.4107

Max Act: 2.2078. Min Act: -0.0002

Data Index: 778908 (C4 (Web Text))

Max Activating Token Index: 46

Text #8

Max Range: 2.4107. Min Range: -2.4107

Max Act: 2.2100. Min Act: -0.0002

Data Index: 449472 (C4 (Web Text))

Max Activating Token Index: 18

Text #9

Max Range: 2.4107. Min Range: -2.4107

Max Act: 2.0643. Min Act: -0.0002

Data Index: 719863 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 2.4107. Min Range: -2.4107

Max Act: 2.0605. Min Act: -0.0002

Data Index: 1218081 (C4 (Web Text))

Max Activating Token Index: 889

Text #11

Max Range: 2.4107. Min Range: -2.4107

Max Act: 2.2056. Min Act: -0.0002

Data Index: 376886 (C4 (Web Text))

Max Activating Token Index: 235

Text #12

Max Range: 2.4107. Min Range: -2.4107

Max Act: 2.0974. Min Act: -0.0002

Data Index: 258511 (C4 (Web Text))

Max Activating Token Index: 371

Text #13

Max Range: 2.4107. Min Range: -2.4107

Max Act: 2.1120. Min Act: -0.0002

Data Index: 687489 (C4 (Web Text))

Max Activating Token Index: 847

Text #14

Max Range: 2.4107. Min Range: -2.4107

Max Act: 2.0350. Min Act: -0.0002

Data Index: 629829 (C4 (Web Text))

Max Activating Token Index: 784

Text #15

Max Range: 2.4107. Min Range: -2.4107

Max Act: 2.0837. Min Act: -0.0002

Data Index: 417433 (C4 (Web Text))

Max Activating Token Index: 399

Text #16

Max Range: 2.4107. Min Range: -2.4107

Max Act: 2.1574. Min Act: -0.0002

Data Index: 927580 (C4 (Web Text))

Max Activating Token Index: 202

Text #17

Max Range: 2.4107. Min Range: -2.4107

Max Act: 2.0212. Min Act: -0.0002

Data Index: 742568 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 2.4107. Min Range: -2.4107

Max Act: 1.9719. Min Act: -0.0002

Data Index: 806930 (C4 (Web Text))

Max Activating Token Index: 115

Text #19

Max Range: 2.4107. Min Range: -2.4107

Max Act: 1.8990. Min Act: -0.0002

Data Index: 1223672 (C4 (Web Text))

Max Activating Token Index: 717