Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1166 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5734. Min Range: -1.5734

Max Act: 1.5734. Min Act: -0.0002

Data Index: 486927 (C4 (Web Text))

Max Activating Token Index: 272

Text #1

Max Range: 1.5734. Min Range: -1.5734

Max Act: 1.5333. Min Act: -0.0002

Data Index: 1138974 (C4 (Web Text))

Max Activating Token Index: 849

Text #2

Max Range: 1.5734. Min Range: -1.5734

Max Act: 1.4180. Min Act: -0.0002

Data Index: 169012 (C4 (Web Text))

Max Activating Token Index: 381

Text #3

Max Range: 1.5734. Min Range: -1.5734

Max Act: 1.4564. Min Act: -0.0002

Data Index: 1205385 (C4 (Web Text))

Max Activating Token Index: 377

Text #4

Max Range: 1.5734. Min Range: -1.5734

Max Act: 1.4574. Min Act: -0.0002

Data Index: 1106516 (C4 (Web Text))

Max Activating Token Index: 431

Text #5

Max Range: 1.5734. Min Range: -1.5734

Max Act: 1.4187. Min Act: -0.0002

Data Index: 425187 (C4 (Web Text))

Max Activating Token Index: 99

Text #6

Max Range: 1.5734. Min Range: -1.5734

Max Act: 1.3979. Min Act: -0.0002

Data Index: 557578 (C4 (Web Text))

Max Activating Token Index: 507

Text #7

Max Range: 1.5734. Min Range: -1.5734

Max Act: 1.3717. Min Act: -0.0002

Data Index: 240834 (C4 (Web Text))

Max Activating Token Index: 921

Text #8

Max Range: 1.5734. Min Range: -1.5734

Max Act: 1.3266. Min Act: -0.0002

Data Index: 853883 (C4 (Web Text))

Max Activating Token Index: 386

Text #9

Max Range: 1.5734. Min Range: -1.5734

Max Act: 1.3637. Min Act: -0.0002

Data Index: 1321400 (C4 (Web Text))

Max Activating Token Index: 929

Text #10

Max Range: 1.5734. Min Range: -1.5734

Max Act: 1.2529. Min Act: -0.0002

Data Index: 964422 (C4 (Web Text))

Max Activating Token Index: 861

Text #11

Max Range: 1.5734. Min Range: -1.5734

Max Act: 1.3212. Min Act: -0.0002

Data Index: 39919 (C4 (Web Text))

Max Activating Token Index: 594

Text #12

Max Range: 1.5734. Min Range: -1.5734

Max Act: 1.2637. Min Act: -0.0002

Data Index: 127768 (C4 (Web Text))

Max Activating Token Index: 298

Text #13

Max Range: 1.5734. Min Range: -1.5734

Max Act: 1.3027. Min Act: -0.0002

Data Index: 596960 (C4 (Web Text))

Max Activating Token Index: 103

Text #14

Max Range: 1.5734. Min Range: -1.5734

Max Act: 1.3077. Min Act: -0.0002

Data Index: 763037 (C4 (Web Text))

Max Activating Token Index: 13

Text #15

Max Range: 1.5734. Min Range: -1.5734

Max Act: 1.2792. Min Act: -0.0002

Data Index: 997500 (C4 (Web Text))

Max Activating Token Index: 209

Text #16

Max Range: 1.5734. Min Range: -1.5734

Max Act: 1.2979. Min Act: -0.0002

Data Index: 496285 (C4 (Web Text))

Max Activating Token Index: 710

Text #17

Max Range: 1.5734. Min Range: -1.5734

Max Act: 1.2707. Min Act: -0.0002

Data Index: 485989 (C4 (Web Text))

Max Activating Token Index: 924

Text #18

Max Range: 1.5734. Min Range: -1.5734

Max Act: 1.2663. Min Act: -0.0002

Data Index: 1304912 (C4 (Web Text))

Max Activating Token Index: 375

Text #19

Max Range: 1.5734. Min Range: -1.5734

Max Act: 1.2843. Min Act: -0.0002

Data Index: 1043580 (C4 (Web Text))

Max Activating Token Index: 509