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

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

Neuron 1716 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2005. Min Range: -2.2005

Max Act: 2.2005. Min Act: -0.0000

Data Index: 240357 (C4 (Web Text))

Max Activating Token Index: 371

Text #1

Max Range: 2.2005. Min Range: -2.2005

Max Act: 1.8596. Min Act: -0.0000

Data Index: 1171039 (C4 (Web Text))

Max Activating Token Index: 790

Text #2

Max Range: 2.2005. Min Range: -2.2005

Max Act: 1.7182. Min Act: -0.0000

Data Index: 869369 (C4 (Web Text))

Max Activating Token Index: 207

Text #3

Max Range: 2.2005. Min Range: -2.2005

Max Act: 1.4975. Min Act: -0.0000

Data Index: 800475 (C4 (Web Text))

Max Activating Token Index: 295

Text #4

Max Range: 2.2005. Min Range: -2.2005

Max Act: 1.4495. Min Act: -0.0001

Data Index: 1286095 (C4 (Web Text))

Max Activating Token Index: 259

Text #5

Max Range: 2.2005. Min Range: -2.2005

Max Act: 1.6610. Min Act: -0.0000

Data Index: 708826 (C4 (Web Text))

Max Activating Token Index: 421

Text #6

Max Range: 2.2005. Min Range: -2.2005

Max Act: 1.6509. Min Act: -0.0000

Data Index: 550465 (C4 (Web Text))

Max Activating Token Index: 406

Text #7

Max Range: 2.2005. Min Range: -2.2005

Max Act: 1.6254. Min Act: -0.0000

Data Index: 831792 (C4 (Web Text))

Max Activating Token Index: 177

Text #8

Max Range: 2.2005. Min Range: -2.2005

Max Act: 1.6743. Min Act: -0.0001

Data Index: 1027743 (C4 (Web Text))

Max Activating Token Index: 211

Text #9

Max Range: 2.2005. Min Range: -2.2005

Max Act: 1.7276. Min Act: -0.0000

Data Index: 92056 (C4 (Web Text))

Max Activating Token Index: 894

Text #10

Max Range: 2.2005. Min Range: -2.2005

Max Act: 1.6608. Min Act: -0.0000

Data Index: 931332 (C4 (Web Text))

Max Activating Token Index: 594

Text #11

Max Range: 2.2005. Min Range: -2.2005

Max Act: 1.6017. Min Act: -0.0000

Data Index: 712868 (C4 (Web Text))

Max Activating Token Index: 626

Text #12

Max Range: 2.2005. Min Range: -2.2005

Max Act: 1.4902. Min Act: -0.0000

Data Index: 581336 (C4 (Web Text))

Max Activating Token Index: 163

Text #13

Max Range: 2.2005. Min Range: -2.2005

Max Act: 1.5158. Min Act: -0.0000

Data Index: 645648 (C4 (Web Text))

Max Activating Token Index: 249

Text #14

Max Range: 2.2005. Min Range: -2.2005

Max Act: 1.5783. Min Act: -0.0000

Data Index: 356341 (C4 (Web Text))

Max Activating Token Index: 330

Text #15

Max Range: 2.2005. Min Range: -2.2005

Max Act: 1.3183. Min Act: -0.0001

Data Index: 293827 (C4 (Web Text))

Max Activating Token Index: 574

Text #16

Max Range: 2.2005. Min Range: -2.2005

Max Act: 1.6919. Min Act: -0.0000

Data Index: 935825 (C4 (Web Text))

Max Activating Token Index: 706

Text #17

Max Range: 2.2005. Min Range: -2.2005

Max Act: 1.4119. Min Act: -0.0000

Data Index: 602994 (C4 (Web Text))

Max Activating Token Index: 720

Text #18

Max Range: 2.2005. Min Range: -2.2005

Max Act: 1.3863. Min Act: -0.0001

Data Index: 1091226 (C4 (Web Text))

Max Activating Token Index: 94

Text #19

Max Range: 2.2005. Min Range: -2.2005

Max Act: 1.3961. Min Act: -0.0000

Data Index: 559492 (C4 (Web Text))

Max Activating Token Index: 160