Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1945 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.1135. Min Act: -0.0002

Data Index: 260219 (C4 (Web Text))

Max Activating Token Index: 337

Text #1

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.1039. Min Act: -0.0002

Data Index: 1350932 (C4 (Web Text))

Max Activating Token Index: 798

Text #2

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.1028. Min Act: -0.0002

Data Index: 360218 (C4 (Web Text))

Max Activating Token Index: 160

Text #3

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.0976. Min Act: -0.0002

Data Index: 81773 (C4 (Web Text))

Max Activating Token Index: 460

Text #4

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.0920. Min Act: -0.0002

Data Index: 862032 (C4 (Web Text))

Max Activating Token Index: 509

Text #5

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.0928. Min Act: -0.0002

Data Index: 771131 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.0900. Min Act: -0.0002

Data Index: 1072949 (C4 (Web Text))

Max Activating Token Index: 947

Text #7

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.0875. Min Act: -0.0002

Data Index: 159746 (C4 (Web Text))

Max Activating Token Index: 899

Text #8

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.0889. Min Act: -0.0002

Data Index: 134842 (C4 (Web Text))

Max Activating Token Index: 465

Text #9

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.0886. Min Act: -0.0002

Data Index: 428710 (C4 (Web Text))

Max Activating Token Index: 682

Text #10

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.0846. Min Act: -0.0002

Data Index: 491166 (C4 (Web Text))

Max Activating Token Index: 612

Text #11

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.0881. Min Act: -0.0002

Data Index: 414043 (C4 (Web Text))

Max Activating Token Index: 947

Text #12

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.0861. Min Act: -0.0002

Data Index: 1007082 (C4 (Web Text))

Max Activating Token Index: 340

Text #13

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.0840. Min Act: -0.0002

Data Index: 314741 (C4 (Web Text))

Max Activating Token Index: 831

Text #14

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.0865. Min Act: -0.0002

Data Index: 243276 (C4 (Web Text))

Max Activating Token Index: 131

Text #15

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.0851. Min Act: -0.0002

Data Index: 710969 (C4 (Web Text))

Max Activating Token Index: 355

Text #16

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.0848. Min Act: -0.0002

Data Index: 583745 (C4 (Web Text))

Max Activating Token Index: 573

Text #17

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.0833. Min Act: -0.0002

Data Index: 353825 (C4 (Web Text))

Max Activating Token Index: 969

Text #18

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.0857. Min Act: -0.0002

Data Index: 755471 (C4 (Web Text))

Max Activating Token Index: 845

Text #19

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.0881. Min Act: -0.0002

Data Index: 1010002 (C4 (Web Text))

Max Activating Token Index: 897