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

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

Neuron 3163 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9816. Min Range: -1.9816

Max Act: 1.9816. Min Act: -0.0001

Data Index: 598144 (C4 (Web Text))

Max Activating Token Index: 81

Text #1

Max Range: 1.9816. Min Range: -1.9816

Max Act: 1.8044. Min Act: -0.0001

Data Index: 1001369 (C4 (Web Text))

Max Activating Token Index: 603

Text #2

Max Range: 1.9816. Min Range: -1.9816

Max Act: 1.8869. Min Act: -0.0001

Data Index: 698252 (C4 (Web Text))

Max Activating Token Index: 4

Text #3

Max Range: 1.9816. Min Range: -1.9816

Max Act: 1.8476. Min Act: -0.0001

Data Index: 639587 (C4 (Web Text))

Max Activating Token Index: 448

Text #4

Max Range: 1.9816. Min Range: -1.9816

Max Act: 1.7790. Min Act: -0.0000

Data Index: 1301366 (C4 (Web Text))

Max Activating Token Index: 187

Text #5

Max Range: 1.9816. Min Range: -1.9816

Max Act: 1.7710. Min Act: -0.0001

Data Index: 1215571 (C4 (Web Text))

Max Activating Token Index: 533

Text #6

Max Range: 1.9816. Min Range: -1.9816

Max Act: 1.7170. Min Act: -0.0000

Data Index: 21154 (C4 (Web Text))

Max Activating Token Index: 261

Text #7

Max Range: 1.9816. Min Range: -1.9816

Max Act: 1.6311. Min Act: -0.0001

Data Index: 981116 (C4 (Web Text))

Max Activating Token Index: 573

Text #8

Max Range: 1.9816. Min Range: -1.9816

Max Act: 1.8830. Min Act: -0.0001

Data Index: 1305667 (C4 (Web Text))

Max Activating Token Index: 674

Text #9

Max Range: 1.9816. Min Range: -1.9816

Max Act: 1.7193. Min Act: -0.0001

Data Index: 976117 (C4 (Web Text))

Max Activating Token Index: 501

Text #10

Max Range: 1.9816. Min Range: -1.9816

Max Act: 1.5892. Min Act: -0.0000

Data Index: 779640 (C4 (Web Text))

Max Activating Token Index: 336

Text #11

Max Range: 1.9816. Min Range: -1.9816

Max Act: 1.8242. Min Act: -0.0001

Data Index: 110676 (C4 (Web Text))

Max Activating Token Index: 790

Text #12

Max Range: 1.9816. Min Range: -1.9816

Max Act: 1.6408. Min Act: -0.0001

Data Index: 1019228 (C4 (Web Text))

Max Activating Token Index: 994

Text #13

Max Range: 1.9816. Min Range: -1.9816

Max Act: 1.6082. Min Act: -0.0001

Data Index: 97475 (C4 (Web Text))

Max Activating Token Index: 509

Text #14

Max Range: 1.9816. Min Range: -1.9816

Max Act: 1.5780. Min Act: -0.0000

Data Index: 530000 (C4 (Web Text))

Max Activating Token Index: 993

Text #15

Max Range: 1.9816. Min Range: -1.9816

Max Act: 1.5571. Min Act: -0.0001

Data Index: 742939 (C4 (Web Text))

Max Activating Token Index: 356

Text #16

Max Range: 1.9816. Min Range: -1.9816

Max Act: 1.5953. Min Act: -0.0000

Data Index: 377400 (C4 (Web Text))

Max Activating Token Index: 525

Text #17

Max Range: 1.9816. Min Range: -1.9816

Max Act: 1.4317. Min Act: -0.0000

Data Index: 897586 (C4 (Web Text))

Max Activating Token Index: 97

Text #18

Max Range: 1.9816. Min Range: -1.9816

Max Act: 1.4143. Min Act: -0.0000

Data Index: 155172 (C4 (Web Text))

Max Activating Token Index: 168

Text #19

Max Range: 1.9816. Min Range: -1.9816

Max Act: 1.3776. Min Act: -0.0000

Data Index: 94923 (C4 (Web Text))

Max Activating Token Index: 942