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

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

Neuron 509 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6114. Min Range: -0.6114

Max Act: 0.6114. Min Act: -0.0000

Data Index: 588304 (C4 (Web Text))

Max Activating Token Index: 948

Text #1

Max Range: 0.6114. Min Range: -0.6114

Max Act: 0.5191. Min Act: -0.0000

Data Index: 236366 (C4 (Web Text))

Max Activating Token Index: 995

Text #2

Max Range: 0.6114. Min Range: -0.6114

Max Act: 0.5149. Min Act: -0.0000

Data Index: 853575 (C4 (Web Text))

Max Activating Token Index: 956

Text #3

Max Range: 0.6114. Min Range: -0.6114

Max Act: 0.4791. Min Act: -0.0000

Data Index: 1035655 (C4 (Web Text))

Max Activating Token Index: 939

Text #4

Max Range: 0.6114. Min Range: -0.6114

Max Act: 0.4812. Min Act: -0.0000

Data Index: 327531 (C4 (Web Text))

Max Activating Token Index: 500

Text #5

Max Range: 0.6114. Min Range: -0.6114

Max Act: 0.4557. Min Act: -0.0000

Data Index: 784171 (C4 (Web Text))

Max Activating Token Index: 1018

Text #6

Max Range: 0.6114. Min Range: -0.6114

Max Act: 0.4717. Min Act: -0.0000

Data Index: 55721 (C4 (Web Text))

Max Activating Token Index: 409

Text #7

Max Range: 0.6114. Min Range: -0.6114

Max Act: 0.4564. Min Act: -0.0000

Data Index: 778104 (C4 (Web Text))

Max Activating Token Index: 390

Text #8

Max Range: 0.6114. Min Range: -0.6114

Max Act: 0.4523. Min Act: -0.0000

Data Index: 886060 (C4 (Web Text))

Max Activating Token Index: 247

Text #9

Max Range: 0.6114. Min Range: -0.6114

Max Act: 0.4788. Min Act: -0.0000

Data Index: 1001084 (C4 (Web Text))

Max Activating Token Index: 984

Text #10

Max Range: 0.6114. Min Range: -0.6114

Max Act: 0.4393. Min Act: -0.0000

Data Index: 613880 (C4 (Web Text))

Max Activating Token Index: 167

Text #11

Max Range: 0.6114. Min Range: -0.6114

Max Act: 0.4417. Min Act: -0.0000

Data Index: 108585 (C4 (Web Text))

Max Activating Token Index: 65

Text #12

Max Range: 0.6114. Min Range: -0.6114

Max Act: 0.4213. Min Act: -0.0000

Data Index: 337219 (C4 (Web Text))

Max Activating Token Index: 310

Text #13

Max Range: 0.6114. Min Range: -0.6114

Max Act: 0.4162. Min Act: -0.0000

Data Index: 108799 (C4 (Web Text))

Max Activating Token Index: 993

Text #14

Max Range: 0.6114. Min Range: -0.6114

Max Act: 0.4700. Min Act: -0.0000

Data Index: 65769 (C4 (Web Text))

Max Activating Token Index: 660

Text #15

Max Range: 0.6114. Min Range: -0.6114

Max Act: 0.4573. Min Act: -0.0000

Data Index: 260798 (C4 (Web Text))

Max Activating Token Index: 187

Text #16

Max Range: 0.6114. Min Range: -0.6114

Max Act: 0.4387. Min Act: -0.0000

Data Index: 1076129 (C4 (Web Text))

Max Activating Token Index: 67

Text #17

Max Range: 0.6114. Min Range: -0.6114

Max Act: 0.4389. Min Act: -0.0000

Data Index: 231133 (C4 (Web Text))

Max Activating Token Index: 115

Text #18

Max Range: 0.6114. Min Range: -0.6114

Max Act: 0.4193. Min Act: -0.0000

Data Index: 1160931 (C4 (Web Text))

Max Activating Token Index: 624

Text #19

Max Range: 0.6114. Min Range: -0.6114

Max Act: 0.4129. Min Act: -0.0000

Data Index: 478945 (C4 (Web Text))

Max Activating Token Index: 540