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

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

Neuron 1293 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9063. Min Range: -4.9063

Max Act: 4.9063. Min Act: -0.0000

Data Index: 778967 (C4 (Web Text))

Max Activating Token Index: 192

Text #1

Max Range: 4.9063. Min Range: -4.9063

Max Act: 4.7097. Min Act: -0.0000

Data Index: 124622 (C4 (Web Text))

Max Activating Token Index: 335

Text #2

Max Range: 4.9063. Min Range: -4.9063

Max Act: 4.6821. Min Act: -0.0000

Data Index: 310988 (C4 (Web Text))

Max Activating Token Index: 636

Text #3

Max Range: 4.9063. Min Range: -4.9063

Max Act: 4.4997. Min Act: -0.0000

Data Index: 144736 (C4 (Web Text))

Max Activating Token Index: 156

Text #4

Max Range: 4.9063. Min Range: -4.9063

Max Act: 3.9112. Min Act: -0.0000

Data Index: 999520 (C4 (Web Text))

Max Activating Token Index: 906

Text #5

Max Range: 4.9063. Min Range: -4.9063

Max Act: 4.0619. Min Act: -0.0000

Data Index: 667620 (C4 (Web Text))

Max Activating Token Index: 109

Text #6

Max Range: 4.9063. Min Range: -4.9063

Max Act: 4.2383. Min Act: -0.0000

Data Index: 727993 (C4 (Web Text))

Max Activating Token Index: 969

Text #7

Max Range: 4.9063. Min Range: -4.9063

Max Act: 3.8392. Min Act: -0.0000

Data Index: 465164 (C4 (Web Text))

Max Activating Token Index: 402

Text #8

Max Range: 4.9063. Min Range: -4.9063

Max Act: 3.9177. Min Act: -0.0000

Data Index: 102877 (C4 (Web Text))

Max Activating Token Index: 970

Text #9

Max Range: 4.9063. Min Range: -4.9063

Max Act: 3.8302. Min Act: -0.0000

Data Index: 1212111 (C4 (Web Text))

Max Activating Token Index: 903

Text #10

Max Range: 4.9063. Min Range: -4.9063

Max Act: 3.7729. Min Act: -0.0000

Data Index: 52790 (C4 (Web Text))

Max Activating Token Index: 613

Text #11

Max Range: 4.9063. Min Range: -4.9063

Max Act: 3.7718. Min Act: -0.0000

Data Index: 1211376 (C4 (Web Text))

Max Activating Token Index: 897

Text #12

Max Range: 4.9063. Min Range: -4.9063

Max Act: 3.5288. Min Act: -0.0000

Data Index: 920091 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 4.9063. Min Range: -4.9063

Max Act: 3.5702. Min Act: -0.0000

Data Index: 1143552 (C4 (Web Text))

Max Activating Token Index: 138

Text #14

Max Range: 4.9063. Min Range: -4.9063

Max Act: 3.6898. Min Act: -0.0000

Data Index: 39393 (C4 (Web Text))

Max Activating Token Index: 269

Text #15

Max Range: 4.9063. Min Range: -4.9063

Max Act: 3.3470. Min Act: -0.0000

Data Index: 61213 (C4 (Web Text))

Max Activating Token Index: 541

Text #16

Max Range: 4.9063. Min Range: -4.9063

Max Act: 3.5037. Min Act: -0.0000

Data Index: 647349 (C4 (Web Text))

Max Activating Token Index: 374

Text #17

Max Range: 4.9063. Min Range: -4.9063

Max Act: 3.7794. Min Act: -0.0000

Data Index: 539305 (C4 (Web Text))

Max Activating Token Index: 604

Text #18

Max Range: 4.9063. Min Range: -4.9063

Max Act: 3.4584. Min Act: -0.0000

Data Index: 1237792 (C4 (Web Text))

Max Activating Token Index: 745

Text #19

Max Range: 4.9063. Min Range: -4.9063

Max Act: 3.4261. Min Act: -0.0000

Data Index: 258317 (C4 (Web Text))

Max Activating Token Index: 837