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

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

Neuron 3785 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9843. Min Range: -3.9843

Max Act: 3.9843. Min Act: -0.0000

Data Index: 1194223 (C4 (Web Text))

Max Activating Token Index: 765

Text #1

Max Range: 3.9843. Min Range: -3.9843

Max Act: 3.3172. Min Act: -0.0000

Data Index: 361135 (C4 (Web Text))

Max Activating Token Index: 101

Text #2

Max Range: 3.9843. Min Range: -3.9843

Max Act: 3.0223. Min Act: -0.0000

Data Index: 1211506 (C4 (Web Text))

Max Activating Token Index: 59

Text #3

Max Range: 3.9843. Min Range: -3.9843

Max Act: 2.5994. Min Act: -0.0000

Data Index: 527669 (C4 (Web Text))

Max Activating Token Index: 174

Text #4

Max Range: 3.9843. Min Range: -3.9843

Max Act: 2.5808. Min Act: -0.0000

Data Index: 461839 (C4 (Web Text))

Max Activating Token Index: 11

Text #5

Max Range: 3.9843. Min Range: -3.9843

Max Act: 2.6294. Min Act: -0.0000

Data Index: 202512 (C4 (Web Text))

Max Activating Token Index: 540

Text #6

Max Range: 3.9843. Min Range: -3.9843

Max Act: 3.1171. Min Act: -0.0000

Data Index: 471912 (C4 (Web Text))

Max Activating Token Index: 624

Text #7

Max Range: 3.9843. Min Range: -3.9843

Max Act: 2.6906. Min Act: -0.0000

Data Index: 1134303 (C4 (Web Text))

Max Activating Token Index: 283

Text #8

Max Range: 3.9843. Min Range: -3.9843

Max Act: 2.6154. Min Act: -0.0000

Data Index: 923655 (C4 (Web Text))

Max Activating Token Index: 102

Text #9

Max Range: 3.9843. Min Range: -3.9843

Max Act: 2.4534. Min Act: -0.0000

Data Index: 1289013 (C4 (Web Text))

Max Activating Token Index: 561

Text #10

Max Range: 3.9843. Min Range: -3.9843

Max Act: 2.4267. Min Act: -0.0000

Data Index: 219155 (C4 (Web Text))

Max Activating Token Index: 776

Text #11

Max Range: 3.9843. Min Range: -3.9843

Max Act: 2.4316. Min Act: -0.0000

Data Index: 845812 (C4 (Web Text))

Max Activating Token Index: 848

Text #12

Max Range: 3.9843. Min Range: -3.9843

Max Act: 2.4345. Min Act: -0.0000

Data Index: 530248 (C4 (Web Text))

Max Activating Token Index: 245

Text #13

Max Range: 3.9843. Min Range: -3.9843

Max Act: 2.2852. Min Act: -0.0000

Data Index: 1118673 (C4 (Web Text))

Max Activating Token Index: 403

Text #14

Max Range: 3.9843. Min Range: -3.9843

Max Act: 2.2832. Min Act: -0.0000

Data Index: 1120698 (C4 (Web Text))

Max Activating Token Index: 994

Text #15

Max Range: 3.9843. Min Range: -3.9843

Max Act: 2.2711. Min Act: -0.0000

Data Index: 242782 (C4 (Web Text))

Max Activating Token Index: 179

Text #16

Max Range: 3.9843. Min Range: -3.9843

Max Act: 2.3943. Min Act: -0.0000

Data Index: 222456 (C4 (Web Text))

Max Activating Token Index: 417

Text #17

Max Range: 3.9843. Min Range: -3.9843

Max Act: 2.5212. Min Act: -0.0000

Data Index: 642317 (C4 (Web Text))

Max Activating Token Index: 981

Text #18

Max Range: 3.9843. Min Range: -3.9843

Max Act: 2.3901. Min Act: -0.0000

Data Index: 1195572 (C4 (Web Text))

Max Activating Token Index: 1000

Text #19

Max Range: 3.9843. Min Range: -3.9843

Max Act: 2.6043. Min Act: -0.0000

Data Index: 31483 (C4 (Web Text))

Max Activating Token Index: 125