Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1034 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.4824. Min Act: -0.0001

Data Index: 506078 (C4 (Web Text))

Max Activating Token Index: 179

Text #1

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.4536. Min Act: -0.0001

Data Index: 394060 (C4 (Web Text))

Max Activating Token Index: 175

Text #2

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.4486. Min Act: -0.0001

Data Index: 513217 (C4 (Web Text))

Max Activating Token Index: 876

Text #3

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.4387. Min Act: -0.0002

Data Index: 676875 (C4 (Web Text))

Max Activating Token Index: 896

Text #4

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.4543. Min Act: -0.0001

Data Index: 9903 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.3875. Min Act: -0.0001

Data Index: 483832 (C4 (Web Text))

Max Activating Token Index: 863

Text #6

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.3920. Min Act: -0.0002

Data Index: 1090755 (C4 (Web Text))

Max Activating Token Index: 777

Text #7

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.3938. Min Act: -0.0002

Data Index: 916760 (C4 (Web Text))

Max Activating Token Index: 324

Text #8

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.4158. Min Act: -0.0002

Data Index: 139052 (C4 (Web Text))

Max Activating Token Index: 147

Text #9

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.3911. Min Act: -0.0002

Data Index: 1126046 (C4 (Web Text))

Max Activating Token Index: 378

Text #10

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.3950. Min Act: -0.0002

Data Index: 933567 (C4 (Web Text))

Max Activating Token Index: 401

Text #11

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.3693. Min Act: -0.0001

Data Index: 46982 (C4 (Web Text))

Max Activating Token Index: 909

Text #12

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.3740. Min Act: -0.0002

Data Index: 407286 (C4 (Web Text))

Max Activating Token Index: 234

Text #13

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.3976. Min Act: -0.0002

Data Index: 585120 (C4 (Web Text))

Max Activating Token Index: 163

Text #14

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.3598. Min Act: -0.0002

Data Index: 1199022 (C4 (Web Text))

Max Activating Token Index: 495

Text #15

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.3816. Min Act: -0.0001

Data Index: 341139 (C4 (Web Text))

Max Activating Token Index: 608

Text #16

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.3531. Min Act: -0.0002

Data Index: 1161893 (C4 (Web Text))

Max Activating Token Index: 559

Text #17

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.3899. Min Act: -0.0001

Data Index: 1260317 (C4 (Web Text))

Max Activating Token Index: 983

Text #18

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.3739. Min Act: -0.0001

Data Index: 163150 (C4 (Web Text))

Max Activating Token Index: 85

Text #19

Max Range: 0.4824. Min Range: -0.4824

Max Act: 0.4035. Min Act: -0.0002

Data Index: 1290122 (C4 (Web Text))

Max Activating Token Index: 87