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

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

Neuron 1036 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: 5.2701. Min Range: -5.2701

Max Act: 5.2701. Min Act: -0.0000

Data Index: 456967 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 5.2701. Min Range: -5.2701

Max Act: 5.0083. Min Act: -0.0000

Data Index: 564017 (C4 (Web Text))

Max Activating Token Index: 99

Text #2

Max Range: 5.2701. Min Range: -5.2701

Max Act: 4.5624. Min Act: -0.0000

Data Index: 703071 (C4 (Web Text))

Max Activating Token Index: 873

Text #3

Max Range: 5.2701. Min Range: -5.2701

Max Act: 4.5370. Min Act: -0.0000

Data Index: 703783 (C4 (Web Text))

Max Activating Token Index: 133

Text #4

Max Range: 5.2701. Min Range: -5.2701

Max Act: 4.0962. Min Act: -0.0000

Data Index: 128114 (C4 (Web Text))

Max Activating Token Index: 1003

Text #5

Max Range: 5.2701. Min Range: -5.2701

Max Act: 4.0419. Min Act: -0.0000

Data Index: 1331480 (C4 (Web Text))

Max Activating Token Index: 970

Text #6

Max Range: 5.2701. Min Range: -5.2701

Max Act: 3.5908. Min Act: -0.0000

Data Index: 98102 (C4 (Web Text))

Max Activating Token Index: 143

Text #7

Max Range: 5.2701. Min Range: -5.2701

Max Act: 3.7880. Min Act: -0.0000

Data Index: 341126 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 5.2701. Min Range: -5.2701

Max Act: 3.7452. Min Act: -0.0000

Data Index: 244986 (C4 (Web Text))

Max Activating Token Index: 7

Text #9

Max Range: 5.2701. Min Range: -5.2701

Max Act: 3.5386. Min Act: -0.0001

Data Index: 173951 (C4 (Web Text))

Max Activating Token Index: 560

Text #10

Max Range: 5.2701. Min Range: -5.2701

Max Act: 3.5709. Min Act: -0.0000

Data Index: 42980 (C4 (Web Text))

Max Activating Token Index: 367

Text #11

Max Range: 5.2701. Min Range: -5.2701

Max Act: 3.5530. Min Act: -0.0000

Data Index: 954924 (C4 (Web Text))

Max Activating Token Index: 337

Text #12

Max Range: 5.2701. Min Range: -5.2701

Max Act: 3.7019. Min Act: -0.0000

Data Index: 1024898 (C4 (Web Text))

Max Activating Token Index: 697

Text #13

Max Range: 5.2701. Min Range: -5.2701

Max Act: 3.6500. Min Act: -0.0000

Data Index: 1070232 (C4 (Web Text))

Max Activating Token Index: 29

Text #14

Max Range: 5.2701. Min Range: -5.2701

Max Act: 3.4782. Min Act: -0.0000

Data Index: 460032 (C4 (Web Text))

Max Activating Token Index: 1013

Text #15

Max Range: 5.2701. Min Range: -5.2701

Max Act: 3.4007. Min Act: -0.0000

Data Index: 1044842 (C4 (Web Text))

Max Activating Token Index: 895

Text #16

Max Range: 5.2701. Min Range: -5.2701

Max Act: 3.7302. Min Act: -0.0000

Data Index: 854674 (C4 (Web Text))

Max Activating Token Index: 19

Text #17

Max Range: 5.2701. Min Range: -5.2701

Max Act: 3.5779. Min Act: -0.0000

Data Index: 1125707 (C4 (Web Text))

Max Activating Token Index: 661

Text #18

Max Range: 5.2701. Min Range: -5.2701

Max Act: 3.3919. Min Act: -0.0000

Data Index: 332960 (C4 (Web Text))

Max Activating Token Index: 102

Text #19

Max Range: 5.2701. Min Range: -5.2701

Max Act: 3.3958. Min Act: -0.0000

Data Index: 1213198 (C4 (Web Text))

Max Activating Token Index: 582