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

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

Neuron 4490 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: 1.3871. Min Range: -1.3871

Max Act: 1.3544. Min Act: -0.0000

Data Index: 415932 (C4 (Web Text))

Max Activating Token Index: 868

Text #1

Max Range: 1.3871. Min Range: -1.3871

Max Act: 1.3701. Min Act: -0.0000

Data Index: 1244685 (C4 (Web Text))

Max Activating Token Index: 356

Text #2

Max Range: 1.3871. Min Range: -1.3871

Max Act: 1.2833. Min Act: -0.0000

Data Index: 148994 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 1.3871. Min Range: -1.3871

Max Act: 1.3871. Min Act: -0.0000

Data Index: 980297 (C4 (Web Text))

Max Activating Token Index: 80

Text #4

Max Range: 1.3871. Min Range: -1.3871

Max Act: 1.3023. Min Act: -0.0000

Data Index: 1043012 (C4 (Web Text))

Max Activating Token Index: 123

Text #5

Max Range: 1.3871. Min Range: -1.3871

Max Act: 1.3791. Min Act: -0.0000

Data Index: 17173 (C4 (Web Text))

Max Activating Token Index: 964

Text #6

Max Range: 1.3871. Min Range: -1.3871

Max Act: 1.0482. Min Act: -0.0000

Data Index: 672271 (C4 (Web Text))

Max Activating Token Index: 860

Text #7

Max Range: 1.3871. Min Range: -1.3871

Max Act: 1.2160. Min Act: -0.0000

Data Index: 978144 (C4 (Web Text))

Max Activating Token Index: 992

Text #8

Max Range: 1.3871. Min Range: -1.3871

Max Act: 1.2556. Min Act: -0.0000

Data Index: 778705 (C4 (Web Text))

Max Activating Token Index: 953

Text #9

Max Range: 1.3871. Min Range: -1.3871

Max Act: 1.3054. Min Act: -0.0000

Data Index: 524196 (C4 (Web Text))

Max Activating Token Index: 411

Text #10

Max Range: 1.3871. Min Range: -1.3871

Max Act: 1.2292. Min Act: -0.0001

Data Index: 1219683 (C4 (Web Text))

Max Activating Token Index: 53

Text #11

Max Range: 1.3871. Min Range: -1.3871

Max Act: 1.2560. Min Act: -0.0000

Data Index: 900832 (C4 (Web Text))

Max Activating Token Index: 624

Text #12

Max Range: 1.3871. Min Range: -1.3871

Max Act: 1.1632. Min Act: -0.0000

Data Index: 340100 (C4 (Web Text))

Max Activating Token Index: 874

Text #13

Max Range: 1.3871. Min Range: -1.3871

Max Act: 1.0695. Min Act: -0.0000

Data Index: 515606 (C4 (Web Text))

Max Activating Token Index: 1022

Text #14

Max Range: 1.3871. Min Range: -1.3871

Max Act: 1.1634. Min Act: -0.0000

Data Index: 375745 (C4 (Web Text))

Max Activating Token Index: 559

Text #15

Max Range: 1.3871. Min Range: -1.3871

Max Act: 1.1207. Min Act: -0.0000

Data Index: 158078 (C4 (Web Text))

Max Activating Token Index: 544

Text #16

Max Range: 1.3871. Min Range: -1.3871

Max Act: 1.1808. Min Act: -0.0000

Data Index: 337756 (C4 (Web Text))

Max Activating Token Index: 92

Text #17

Max Range: 1.3871. Min Range: -1.3871

Max Act: 1.1099. Min Act: -0.0000

Data Index: 428638 (C4 (Web Text))

Max Activating Token Index: 506

Text #18

Max Range: 1.3871. Min Range: -1.3871

Max Act: 1.1187. Min Act: -0.0000

Data Index: 140815 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 1.3871. Min Range: -1.3871

Max Act: 1.1768. Min Act: -0.0001

Data Index: 359749 (C4 (Web Text))

Max Activating Token Index: 270