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

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

Neuron 1536 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: 0.0958. Min Range: -0.0958

Max Act: 0.0958. Min Act: -0.0001

Data Index: 1008291 (C4 (Web Text))

Max Activating Token Index: 214

Text #1

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0938. Min Act: -0.0002

Data Index: 132792 (C4 (Web Text))

Max Activating Token Index: 473

Text #2

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0935. Min Act: -0.0001

Data Index: 802525 (C4 (Web Text))

Max Activating Token Index: 833

Text #3

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0838. Min Act: -0.0002

Data Index: 542350 (C4 (Web Text))

Max Activating Token Index: 587

Text #4

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0857. Min Act: -0.0002

Data Index: 1017453 (C4 (Web Text))

Max Activating Token Index: 742

Text #5

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0712. Min Act: -0.0001

Data Index: 1179762 (C4 (Web Text))

Max Activating Token Index: 92

Text #6

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0717. Min Act: -0.0001

Data Index: 284909 (C4 (Web Text))

Max Activating Token Index: 328

Text #7

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0709. Min Act: -0.0002

Data Index: 332921 (C4 (Web Text))

Max Activating Token Index: 81

Text #8

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0666. Min Act: -0.0001

Data Index: 163955 (C4 (Web Text))

Max Activating Token Index: 188

Text #9

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0667. Min Act: -0.0002

Data Index: 97708 (C4 (Web Text))

Max Activating Token Index: 264

Text #10

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0675. Min Act: -0.0002

Data Index: 1534762 (Python Code)

Max Activating Token Index: 306

Text #11

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0658. Min Act: -0.0002

Data Index: 385594 (C4 (Web Text))

Max Activating Token Index: 317

Text #12

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0644. Min Act: -0.0002

Data Index: 485033 (C4 (Web Text))

Max Activating Token Index: 97

Text #13

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0665. Min Act: -0.0002

Data Index: 984835 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0642. Min Act: -0.0001

Data Index: 609057 (C4 (Web Text))

Max Activating Token Index: 69

Text #15

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0671. Min Act: -0.0001

Data Index: 97320 (C4 (Web Text))

Max Activating Token Index: 405

Text #16

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0633. Min Act: -0.0001

Data Index: 1003089 (C4 (Web Text))

Max Activating Token Index: 169

Text #17

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0667. Min Act: -0.0002

Data Index: 1075054 (C4 (Web Text))

Max Activating Token Index: 518

Text #18

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0643. Min Act: -0.0002

Data Index: 1280137 (C4 (Web Text))

Max Activating Token Index: 996

Text #19

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0629. Min Act: -0.0002

Data Index: 137933 (C4 (Web Text))

Max Activating Token Index: 218