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

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

Neuron 3042 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3070. Min Range: -1.3070

Max Act: 1.3070. Min Act: -0.0001

Data Index: 457548 (C4 (Web Text))

Max Activating Token Index: 754

Text #1

Max Range: 1.3070. Min Range: -1.3070

Max Act: 1.1901. Min Act: -0.0001

Data Index: 1092436 (C4 (Web Text))

Max Activating Token Index: 936

Text #2

Max Range: 1.3070. Min Range: -1.3070

Max Act: 1.1054. Min Act: -0.0000

Data Index: 1357932 (C4 (Web Text))

Max Activating Token Index: 689

Text #3

Max Range: 1.3070. Min Range: -1.3070

Max Act: 1.1277. Min Act: -0.0001

Data Index: 1501283 (Python Code)

Max Activating Token Index: 101

Text #4

Max Range: 1.3070. Min Range: -1.3070

Max Act: 1.0874. Min Act: -0.0001

Data Index: 378346 (C4 (Web Text))

Max Activating Token Index: 621

Text #5

Max Range: 1.3070. Min Range: -1.3070

Max Act: 1.1262. Min Act: -0.0001

Data Index: 412328 (C4 (Web Text))

Max Activating Token Index: 555

Text #6

Max Range: 1.3070. Min Range: -1.3070

Max Act: 1.0764. Min Act: -0.0001

Data Index: 287536 (C4 (Web Text))

Max Activating Token Index: 733

Text #7

Max Range: 1.3070. Min Range: -1.3070

Max Act: 1.0714. Min Act: -0.0001

Data Index: 822422 (C4 (Web Text))

Max Activating Token Index: 822

Text #8

Max Range: 1.3070. Min Range: -1.3070

Max Act: 1.1430. Min Act: -0.0001

Data Index: 1608343 (Python Code)

Max Activating Token Index: 113

Text #9

Max Range: 1.3070. Min Range: -1.3070

Max Act: 1.1091. Min Act: -0.0000

Data Index: 1474044 (Python Code)

Max Activating Token Index: 118

Text #10

Max Range: 1.3070. Min Range: -1.3070

Max Act: 1.0251. Min Act: -0.0001

Data Index: 110863 (C4 (Web Text))

Max Activating Token Index: 489

Text #11

Max Range: 1.3070. Min Range: -1.3070

Max Act: 1.0868. Min Act: -0.0001

Data Index: 463727 (C4 (Web Text))

Max Activating Token Index: 838

Text #12

Max Range: 1.3070. Min Range: -1.3070

Max Act: 1.1049. Min Act: -0.0001

Data Index: 349461 (C4 (Web Text))

Max Activating Token Index: 312

Text #13

Max Range: 1.3070. Min Range: -1.3070

Max Act: 1.0361. Min Act: -0.0001

Data Index: 1164684 (C4 (Web Text))

Max Activating Token Index: 191

Text #14

Max Range: 1.3070. Min Range: -1.3070

Max Act: 0.9793. Min Act: -0.0001

Data Index: 745638 (C4 (Web Text))

Max Activating Token Index: 884

Text #15

Max Range: 1.3070. Min Range: -1.3070

Max Act: 1.0334. Min Act: -0.0001

Data Index: 1363218 (Python Code)

Max Activating Token Index: 241

Text #16

Max Range: 1.3070. Min Range: -1.3070

Max Act: 1.0464. Min Act: -0.0001

Data Index: 261014 (C4 (Web Text))

Max Activating Token Index: 581

Text #17

Max Range: 1.3070. Min Range: -1.3070

Max Act: 0.9838. Min Act: -0.0001

Data Index: 270312 (C4 (Web Text))

Max Activating Token Index: 186

Text #18

Max Range: 1.3070. Min Range: -1.3070

Max Act: 0.9507. Min Act: -0.0001

Data Index: 1043830 (C4 (Web Text))

Max Activating Token Index: 588

Text #19

Max Range: 1.3070. Min Range: -1.3070

Max Act: 1.0424. Min Act: -0.0001

Data Index: 1342139 (C4 (Web Text))

Max Activating Token Index: 715