Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 2023 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.1093. Min Act: -0.0002

Data Index: 933269 (C4 (Web Text))

Max Activating Token Index: 303

Text #1

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.1105. Min Act: -0.0002

Data Index: 471805 (C4 (Web Text))

Max Activating Token Index: 506

Text #2

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.1002. Min Act: -0.0002

Data Index: 627692 (C4 (Web Text))

Max Activating Token Index: 244

Text #3

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0915. Min Act: -0.0002

Data Index: 1105464 (C4 (Web Text))

Max Activating Token Index: 544

Text #4

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0984. Min Act: -0.0002

Data Index: 1262479 (C4 (Web Text))

Max Activating Token Index: 837

Text #5

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0914. Min Act: -0.0001

Data Index: 428031 (C4 (Web Text))

Max Activating Token Index: 168

Text #6

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0872. Min Act: -0.0002

Data Index: 876745 (C4 (Web Text))

Max Activating Token Index: 242

Text #7

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0876. Min Act: -0.0002

Data Index: 534459 (C4 (Web Text))

Max Activating Token Index: 286

Text #8

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0859. Min Act: -0.0002

Data Index: 183990 (C4 (Web Text))

Max Activating Token Index: 365

Text #9

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0880. Min Act: -0.0002

Data Index: 313054 (C4 (Web Text))

Max Activating Token Index: 780

Text #10

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0877. Min Act: -0.0001

Data Index: 388990 (C4 (Web Text))

Max Activating Token Index: 663

Text #11

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0839. Min Act: -0.0001

Data Index: 549349 (C4 (Web Text))

Max Activating Token Index: 874

Text #12

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0827. Min Act: -0.0002

Data Index: 270695 (C4 (Web Text))

Max Activating Token Index: 531

Text #13

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0842. Min Act: -0.0001

Data Index: 407567 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0847. Min Act: -0.0002

Data Index: 444020 (C4 (Web Text))

Max Activating Token Index: 827

Text #15

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0820. Min Act: -0.0002

Data Index: 864555 (C4 (Web Text))

Max Activating Token Index: 439

Text #16

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0820. Min Act: -0.0002

Data Index: 909041 (C4 (Web Text))

Max Activating Token Index: 691

Text #17

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0858. Min Act: -0.0002

Data Index: 726703 (C4 (Web Text))

Max Activating Token Index: 560

Text #18

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0826. Min Act: -0.0002

Data Index: 1286487 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0858. Min Act: -0.0002

Data Index: 1261909 (C4 (Web Text))

Max Activating Token Index: 825