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

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

Neuron 2392 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7043. Min Range: -0.7043

Max Act: 0.7043. Min Act: -0.0000

Data Index: 584054 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 0.7043. Min Range: -0.7043

Max Act: 0.6615. Min Act: -0.0000

Data Index: 1163852 (C4 (Web Text))

Max Activating Token Index: 612

Text #2

Max Range: 0.7043. Min Range: -0.7043

Max Act: 0.6583. Min Act: -0.0000

Data Index: 1003778 (C4 (Web Text))

Max Activating Token Index: 927

Text #3

Max Range: 0.7043. Min Range: -0.7043

Max Act: 0.6061. Min Act: -0.0000

Data Index: 283112 (C4 (Web Text))

Max Activating Token Index: 872

Text #4

Max Range: 0.7043. Min Range: -0.7043

Max Act: 0.5850. Min Act: -0.0000

Data Index: 631538 (C4 (Web Text))

Max Activating Token Index: 126

Text #5

Max Range: 0.7043. Min Range: -0.7043

Max Act: 0.5856. Min Act: -0.0000

Data Index: 1532292 (Python Code)

Max Activating Token Index: 401

Text #6

Max Range: 0.7043. Min Range: -0.7043

Max Act: 0.5531. Min Act: -0.0000

Data Index: 567052 (C4 (Web Text))

Max Activating Token Index: 582

Text #7

Max Range: 0.7043. Min Range: -0.7043

Max Act: 0.5504. Min Act: -0.0000

Data Index: 684557 (C4 (Web Text))

Max Activating Token Index: 77

Text #8

Max Range: 0.7043. Min Range: -0.7043

Max Act: 0.5711. Min Act: -0.0000

Data Index: 1007786 (C4 (Web Text))

Max Activating Token Index: 377

Text #9

Max Range: 0.7043. Min Range: -0.7043

Max Act: 0.5433. Min Act: -0.0000

Data Index: 93876 (C4 (Web Text))

Max Activating Token Index: 892

Text #10

Max Range: 0.7043. Min Range: -0.7043

Max Act: 0.5322. Min Act: -0.0000

Data Index: 536247 (C4 (Web Text))

Max Activating Token Index: 1008

Text #11

Max Range: 0.7043. Min Range: -0.7043

Max Act: 0.5621. Min Act: -0.0000

Data Index: 105622 (C4 (Web Text))

Max Activating Token Index: 882

Text #12

Max Range: 0.7043. Min Range: -0.7043

Max Act: 0.5543. Min Act: -0.0000

Data Index: 333875 (C4 (Web Text))

Max Activating Token Index: 215

Text #13

Max Range: 0.7043. Min Range: -0.7043

Max Act: 0.5352. Min Act: -0.0000

Data Index: 1536317 (Python Code)

Max Activating Token Index: 303

Text #14

Max Range: 0.7043. Min Range: -0.7043

Max Act: 0.5421. Min Act: -0.0000

Data Index: 179249 (C4 (Web Text))

Max Activating Token Index: 869

Text #15

Max Range: 0.7043. Min Range: -0.7043

Max Act: 0.5227. Min Act: 0.0000

Data Index: 341104 (C4 (Web Text))

Max Activating Token Index: 1011

Text #16

Max Range: 0.7043. Min Range: -0.7043

Max Act: 0.5033. Min Act: -0.0000

Data Index: 1318223 (C4 (Web Text))

Max Activating Token Index: 818

Text #17

Max Range: 0.7043. Min Range: -0.7043

Max Act: 0.5195. Min Act: -0.0000

Data Index: 731986 (C4 (Web Text))

Max Activating Token Index: 117

Text #18

Max Range: 0.7043. Min Range: -0.7043

Max Act: 0.5153. Min Act: -0.0000

Data Index: 814131 (C4 (Web Text))

Max Activating Token Index: 744

Text #19

Max Range: 0.7043. Min Range: -0.7043

Max Act: 0.5120. Min Act: -0.0000

Data Index: 926730 (C4 (Web Text))

Max Activating Token Index: 614