Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3954 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4010. Min Range: -1.4010

Max Act: 1.4010. Min Act: -0.0002

Data Index: 933897 (C4 (Web Text))

Max Activating Token Index: 831

Text #1

Max Range: 1.4010. Min Range: -1.4010

Max Act: 1.3096. Min Act: -0.0002

Data Index: 1093358 (C4 (Web Text))

Max Activating Token Index: 366

Text #2

Max Range: 1.4010. Min Range: -1.4010

Max Act: 1.1159. Min Act: -0.0001

Data Index: 385494 (C4 (Web Text))

Max Activating Token Index: 798

Text #3

Max Range: 1.4010. Min Range: -1.4010

Max Act: 1.2116. Min Act: -0.0002

Data Index: 69992 (C4 (Web Text))

Max Activating Token Index: 808

Text #4

Max Range: 1.4010. Min Range: -1.4010

Max Act: 1.2452. Min Act: -0.0002

Data Index: 386048 (C4 (Web Text))

Max Activating Token Index: 61

Text #5

Max Range: 1.4010. Min Range: -1.4010

Max Act: 1.1634. Min Act: -0.0001

Data Index: 992960 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 1.4010. Min Range: -1.4010

Max Act: 1.1474. Min Act: -0.0002

Data Index: 258324 (C4 (Web Text))

Max Activating Token Index: 45

Text #7

Max Range: 1.4010. Min Range: -1.4010

Max Act: 1.0370. Min Act: -0.0002

Data Index: 357531 (C4 (Web Text))

Max Activating Token Index: 823

Text #8

Max Range: 1.4010. Min Range: -1.4010

Max Act: 1.1071. Min Act: -0.0001

Data Index: 237173 (C4 (Web Text))

Max Activating Token Index: 257

Text #9

Max Range: 1.4010. Min Range: -1.4010

Max Act: 1.1869. Min Act: -0.0002

Data Index: 466304 (C4 (Web Text))

Max Activating Token Index: 655

Text #10

Max Range: 1.4010. Min Range: -1.4010

Max Act: 1.1190. Min Act: -0.0002

Data Index: 28424 (C4 (Web Text))

Max Activating Token Index: 887

Text #11

Max Range: 1.4010. Min Range: -1.4010

Max Act: 0.9848. Min Act: -0.0001

Data Index: 1134762 (C4 (Web Text))

Max Activating Token Index: 573

Text #12

Max Range: 1.4010. Min Range: -1.4010

Max Act: 1.1179. Min Act: -0.0002

Data Index: 443728 (C4 (Web Text))

Max Activating Token Index: 663

Text #13

Max Range: 1.4010. Min Range: -1.4010

Max Act: 1.1421. Min Act: -0.0001

Data Index: 877987 (C4 (Web Text))

Max Activating Token Index: 883

Text #14

Max Range: 1.4010. Min Range: -1.4010

Max Act: 1.0768. Min Act: -0.0001

Data Index: 166341 (C4 (Web Text))

Max Activating Token Index: 166

Text #15

Max Range: 1.4010. Min Range: -1.4010

Max Act: 1.0883. Min Act: -0.0002

Data Index: 1067981 (C4 (Web Text))

Max Activating Token Index: 591

Text #16

Max Range: 1.4010. Min Range: -1.4010

Max Act: 1.0417. Min Act: -0.0001

Data Index: 1227723 (C4 (Web Text))

Max Activating Token Index: 292

Text #17

Max Range: 1.4010. Min Range: -1.4010

Max Act: 1.0632. Min Act: -0.0001

Data Index: 767856 (C4 (Web Text))

Max Activating Token Index: 167

Text #18

Max Range: 1.4010. Min Range: -1.4010

Max Act: 1.0252. Min Act: -0.0001

Data Index: 1000668 (C4 (Web Text))

Max Activating Token Index: 909

Text #19

Max Range: 1.4010. Min Range: -1.4010

Max Act: 1.1199. Min Act: -0.0002

Data Index: 207326 (C4 (Web Text))

Max Activating Token Index: 643