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

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

Neuron 2539 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4958. Min Range: -0.4958

Max Act: 0.4958. Min Act: -0.0002

Data Index: 1201926 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 0.4958. Min Range: -0.4958

Max Act: 0.4688. Min Act: -0.0002

Data Index: 12700 (C4 (Web Text))

Max Activating Token Index: 849

Text #2

Max Range: 0.4958. Min Range: -0.4958

Max Act: 0.4641. Min Act: -0.0002

Data Index: 1032408 (C4 (Web Text))

Max Activating Token Index: 385

Text #3

Max Range: 0.4958. Min Range: -0.4958

Max Act: 0.4226. Min Act: -0.0002

Data Index: 629082 (C4 (Web Text))

Max Activating Token Index: 824

Text #4

Max Range: 0.4958. Min Range: -0.4958

Max Act: 0.3715. Min Act: -0.0002

Data Index: 964350 (C4 (Web Text))

Max Activating Token Index: 636

Text #5

Max Range: 0.4958. Min Range: -0.4958

Max Act: 0.3801. Min Act: -0.0002

Data Index: 1035126 (C4 (Web Text))

Max Activating Token Index: 299

Text #6

Max Range: 0.4958. Min Range: -0.4958

Max Act: 0.4431. Min Act: -0.0002

Data Index: 768125 (C4 (Web Text))

Max Activating Token Index: 871

Text #7

Max Range: 0.4958. Min Range: -0.4958

Max Act: 0.3986. Min Act: -0.0002

Data Index: 34644 (C4 (Web Text))

Max Activating Token Index: 288

Text #8

Max Range: 0.4958. Min Range: -0.4958

Max Act: 0.3665. Min Act: -0.0002

Data Index: 1164031 (C4 (Web Text))

Max Activating Token Index: 978

Text #9

Max Range: 0.4958. Min Range: -0.4958

Max Act: 0.3788. Min Act: -0.0002

Data Index: 714797 (C4 (Web Text))

Max Activating Token Index: 963

Text #10

Max Range: 0.4958. Min Range: -0.4958

Max Act: 0.3920. Min Act: -0.0002

Data Index: 840634 (C4 (Web Text))

Max Activating Token Index: 717

Text #11

Max Range: 0.4958. Min Range: -0.4958

Max Act: 0.3917. Min Act: -0.0002

Data Index: 992011 (C4 (Web Text))

Max Activating Token Index: 934

Text #12

Max Range: 0.4958. Min Range: -0.4958

Max Act: 0.3421. Min Act: -0.0002

Data Index: 183826 (C4 (Web Text))

Max Activating Token Index: 739

Text #13

Max Range: 0.4958. Min Range: -0.4958

Max Act: 0.4081. Min Act: -0.0002

Data Index: 1164203 (C4 (Web Text))

Max Activating Token Index: 21

Text #14

Max Range: 0.4958. Min Range: -0.4958

Max Act: 0.3875. Min Act: -0.0002

Data Index: 1307204 (C4 (Web Text))

Max Activating Token Index: 7

Text #15

Max Range: 0.4958. Min Range: -0.4958

Max Act: 0.3748. Min Act: -0.0002

Data Index: 417378 (C4 (Web Text))

Max Activating Token Index: 447

Text #16

Max Range: 0.4958. Min Range: -0.4958

Max Act: 0.3574. Min Act: -0.0002

Data Index: 1085781 (C4 (Web Text))

Max Activating Token Index: 24

Text #17

Max Range: 0.4958. Min Range: -0.4958

Max Act: 0.3656. Min Act: -0.0002

Data Index: 1333378 (C4 (Web Text))

Max Activating Token Index: 178

Text #18

Max Range: 0.4958. Min Range: -0.4958

Max Act: 0.3291. Min Act: -0.0002

Data Index: 944434 (C4 (Web Text))

Max Activating Token Index: 807

Text #19

Max Range: 0.4958. Min Range: -0.4958

Max Act: 0.3691. Min Act: -0.0002

Data Index: 706046 (C4 (Web Text))

Max Activating Token Index: 881