Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4207 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.7078. Min Range: -1.7078

Max Act: 1.7078. Min Act: -0.0003

Data Index: 169458 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 1.7078. Min Range: -1.7078

Max Act: 1.6346. Min Act: -0.0003

Data Index: 61342 (C4 (Web Text))

Max Activating Token Index: 30

Text #2

Max Range: 1.7078. Min Range: -1.7078

Max Act: 1.6611. Min Act: -0.0003

Data Index: 48842 (C4 (Web Text))

Max Activating Token Index: 157

Text #3

Max Range: 1.7078. Min Range: -1.7078

Max Act: 1.5684. Min Act: -0.0003

Data Index: 799005 (C4 (Web Text))

Max Activating Token Index: 38

Text #4

Max Range: 1.7078. Min Range: -1.7078

Max Act: 1.6166. Min Act: -0.0003

Data Index: 449055 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 1.7078. Min Range: -1.7078

Max Act: 1.4815. Min Act: -0.0003

Data Index: 947906 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 1.7078. Min Range: -1.7078

Max Act: 1.4124. Min Act: -0.0002

Data Index: 230106 (C4 (Web Text))

Max Activating Token Index: 131

Text #7

Max Range: 1.7078. Min Range: -1.7078

Max Act: 1.4655. Min Act: -0.0003

Data Index: 1198755 (C4 (Web Text))

Max Activating Token Index: 65

Text #8

Max Range: 1.7078. Min Range: -1.7078

Max Act: 1.4521. Min Act: -0.0003

Data Index: 189385 (C4 (Web Text))

Max Activating Token Index: 61

Text #9

Max Range: 1.7078. Min Range: -1.7078

Max Act: 1.4517. Min Act: -0.0003

Data Index: 962955 (C4 (Web Text))

Max Activating Token Index: 243

Text #10

Max Range: 1.7078. Min Range: -1.7078

Max Act: 1.4460. Min Act: -0.0003

Data Index: 744015 (C4 (Web Text))

Max Activating Token Index: 72

Text #11

Max Range: 1.7078. Min Range: -1.7078

Max Act: 1.4365. Min Act: -0.0003

Data Index: 423177 (C4 (Web Text))

Max Activating Token Index: 62

Text #12

Max Range: 1.7078. Min Range: -1.7078

Max Act: 1.4049. Min Act: -0.0003

Data Index: 1174804 (C4 (Web Text))

Max Activating Token Index: 229

Text #13

Max Range: 1.7078. Min Range: -1.7078

Max Act: 1.4029. Min Act: -0.0003

Data Index: 966896 (C4 (Web Text))

Max Activating Token Index: 360

Text #14

Max Range: 1.7078. Min Range: -1.7078

Max Act: 1.3943. Min Act: -0.0003

Data Index: 546715 (C4 (Web Text))

Max Activating Token Index: 507

Text #15

Max Range: 1.7078. Min Range: -1.7078

Max Act: 1.3211. Min Act: -0.0003

Data Index: 1205998 (C4 (Web Text))

Max Activating Token Index: 281

Text #16

Max Range: 1.7078. Min Range: -1.7078

Max Act: 1.3191. Min Act: -0.0003

Data Index: 655746 (C4 (Web Text))

Max Activating Token Index: 102

Text #17

Max Range: 1.7078. Min Range: -1.7078

Max Act: 1.3319. Min Act: -0.0003

Data Index: 499615 (C4 (Web Text))

Max Activating Token Index: 358

Text #18

Max Range: 1.7078. Min Range: -1.7078

Max Act: 1.3221. Min Act: -0.0002

Data Index: 86164 (C4 (Web Text))

Max Activating Token Index: 363

Text #19

Max Range: 1.7078. Min Range: -1.7078

Max Act: 1.3256. Min Act: -0.0003

Data Index: 725797 (C4 (Web Text))

Max Activating Token Index: 681