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

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

Neuron 4992 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3046. Min Range: -1.3046

Max Act: 1.1883. Min Act: -0.0000

Data Index: 700424 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 1.3046. Min Range: -1.3046

Max Act: 1.0330. Min Act: -0.0000

Data Index: 422133 (C4 (Web Text))

Max Activating Token Index: 396

Text #2

Max Range: 1.3046. Min Range: -1.3046

Max Act: 1.0344. Min Act: -0.0000

Data Index: 1031755 (C4 (Web Text))

Max Activating Token Index: 926

Text #3

Max Range: 1.3046. Min Range: -1.3046

Max Act: 1.0868. Min Act: -0.0000

Data Index: 644452 (C4 (Web Text))

Max Activating Token Index: 347

Text #4

Max Range: 1.3046. Min Range: -1.3046

Max Act: 1.3046. Min Act: -0.0000

Data Index: 477140 (C4 (Web Text))

Max Activating Token Index: 156

Text #5

Max Range: 1.3046. Min Range: -1.3046

Max Act: 1.0558. Min Act: -0.0000

Data Index: 371601 (C4 (Web Text))

Max Activating Token Index: 969

Text #6

Max Range: 1.3046. Min Range: -1.3046

Max Act: 1.0860. Min Act: -0.0000

Data Index: 982917 (C4 (Web Text))

Max Activating Token Index: 50

Text #7

Max Range: 1.3046. Min Range: -1.3046

Max Act: 1.0780. Min Act: -0.0000

Data Index: 521075 (C4 (Web Text))

Max Activating Token Index: 75

Text #8

Max Range: 1.3046. Min Range: -1.3046

Max Act: 0.9718. Min Act: -0.0000

Data Index: 403234 (C4 (Web Text))

Max Activating Token Index: 713

Text #9

Max Range: 1.3046. Min Range: -1.3046

Max Act: 0.9759. Min Act: 0.0000

Data Index: 309276 (C4 (Web Text))

Max Activating Token Index: 534

Text #10

Max Range: 1.3046. Min Range: -1.3046

Max Act: 1.0202. Min Act: -0.0000

Data Index: 1182333 (C4 (Web Text))

Max Activating Token Index: 971

Text #11

Max Range: 1.3046. Min Range: -1.3046

Max Act: 1.0176. Min Act: -0.0000

Data Index: 1012684 (C4 (Web Text))

Max Activating Token Index: 457

Text #12

Max Range: 1.3046. Min Range: -1.3046

Max Act: 0.8419. Min Act: -0.0000

Data Index: 886944 (C4 (Web Text))

Max Activating Token Index: 840

Text #13

Max Range: 1.3046. Min Range: -1.3046

Max Act: 0.8991. Min Act: -0.0000

Data Index: 231353 (C4 (Web Text))

Max Activating Token Index: 247

Text #14

Max Range: 1.3046. Min Range: -1.3046

Max Act: 0.9886. Min Act: -0.0000

Data Index: 768809 (C4 (Web Text))

Max Activating Token Index: 118

Text #15

Max Range: 1.3046. Min Range: -1.3046

Max Act: 1.0493. Min Act: -0.0000

Data Index: 704080 (C4 (Web Text))

Max Activating Token Index: 912

Text #16

Max Range: 1.3046. Min Range: -1.3046

Max Act: 0.9735. Min Act: -0.0000

Data Index: 862248 (C4 (Web Text))

Max Activating Token Index: 586

Text #17

Max Range: 1.3046. Min Range: -1.3046

Max Act: 0.8509. Min Act: -0.0000

Data Index: 146726 (C4 (Web Text))

Max Activating Token Index: 742

Text #18

Max Range: 1.3046. Min Range: -1.3046

Max Act: 0.9931. Min Act: -0.0000

Data Index: 1129312 (C4 (Web Text))

Max Activating Token Index: 903

Text #19

Max Range: 1.3046. Min Range: -1.3046

Max Act: 0.9695. Min Act: -0.0000

Data Index: 1197974 (C4 (Web Text))

Max Activating Token Index: 989