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

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

Neuron 4612 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5509. Min Range: -5.5509

Max Act: 5.3181. Min Act: -0.0000

Data Index: 768419 (C4 (Web Text))

Max Activating Token Index: 593

Text #1

Max Range: 5.5509. Min Range: -5.5509

Max Act: 5.5509. Min Act: -0.0000

Data Index: 83464 (C4 (Web Text))

Max Activating Token Index: 982

Text #2

Max Range: 5.5509. Min Range: -5.5509

Max Act: 4.9611. Min Act: -0.0000

Data Index: 653286 (C4 (Web Text))

Max Activating Token Index: 976

Text #3

Max Range: 5.5509. Min Range: -5.5509

Max Act: 4.3460. Min Act: -0.0000

Data Index: 1051449 (C4 (Web Text))

Max Activating Token Index: 573

Text #4

Max Range: 5.5509. Min Range: -5.5509

Max Act: 4.0247. Min Act: -0.0000

Data Index: 524178 (C4 (Web Text))

Max Activating Token Index: 810

Text #5

Max Range: 5.5509. Min Range: -5.5509

Max Act: 3.9308. Min Act: -0.0000

Data Index: 786906 (C4 (Web Text))

Max Activating Token Index: 108

Text #6

Max Range: 5.5509. Min Range: -5.5509

Max Act: 3.9361. Min Act: -0.0000

Data Index: 412081 (C4 (Web Text))

Max Activating Token Index: 1019

Text #7

Max Range: 5.5509. Min Range: -5.5509

Max Act: 3.7089. Min Act: -0.0000

Data Index: 894070 (C4 (Web Text))

Max Activating Token Index: 1011

Text #8

Max Range: 5.5509. Min Range: -5.5509

Max Act: 3.6866. Min Act: -0.0000

Data Index: 473104 (C4 (Web Text))

Max Activating Token Index: 58

Text #9

Max Range: 5.5509. Min Range: -5.5509

Max Act: 3.5214. Min Act: -0.0000

Data Index: 14324 (C4 (Web Text))

Max Activating Token Index: 667

Text #10

Max Range: 5.5509. Min Range: -5.5509

Max Act: 3.8058. Min Act: -0.0000

Data Index: 160255 (C4 (Web Text))

Max Activating Token Index: 600

Text #11

Max Range: 5.5509. Min Range: -5.5509

Max Act: 3.8921. Min Act: -0.0000

Data Index: 1337719 (C4 (Web Text))

Max Activating Token Index: 137

Text #12

Max Range: 5.5509. Min Range: -5.5509

Max Act: 3.8609. Min Act: -0.0000

Data Index: 987150 (C4 (Web Text))

Max Activating Token Index: 86

Text #13

Max Range: 5.5509. Min Range: -5.5509

Max Act: 3.4645. Min Act: -0.0000

Data Index: 514742 (C4 (Web Text))

Max Activating Token Index: 83

Text #14

Max Range: 5.5509. Min Range: -5.5509

Max Act: 3.5149. Min Act: -0.0000

Data Index: 1113292 (C4 (Web Text))

Max Activating Token Index: 822

Text #15

Max Range: 5.5509. Min Range: -5.5509

Max Act: 3.5215. Min Act: -0.0000

Data Index: 723480 (C4 (Web Text))

Max Activating Token Index: 936

Text #16

Max Range: 5.5509. Min Range: -5.5509

Max Act: 3.4915. Min Act: -0.0000

Data Index: 1186365 (C4 (Web Text))

Max Activating Token Index: 493

Text #17

Max Range: 5.5509. Min Range: -5.5509

Max Act: 3.1968. Min Act: -0.0000

Data Index: 46632 (C4 (Web Text))

Max Activating Token Index: 914

Text #18

Max Range: 5.5509. Min Range: -5.5509

Max Act: 3.0232. Min Act: -0.0000

Data Index: 825876 (C4 (Web Text))

Max Activating Token Index: 880

Text #19

Max Range: 5.5509. Min Range: -5.5509

Max Act: 2.9697. Min Act: -0.0000

Data Index: 563392 (C4 (Web Text))

Max Activating Token Index: 941