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

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

Neuron 1755 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: 0.7621. Min Range: -0.7621

Max Act: 0.7561. Min Act: -0.0002

Data Index: 755870 (C4 (Web Text))

Max Activating Token Index: 267

Text #1

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.7621. Min Act: -0.0002

Data Index: 617402 (C4 (Web Text))

Max Activating Token Index: 412

Text #2

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.6606. Min Act: -0.0002

Data Index: 541312 (C4 (Web Text))

Max Activating Token Index: 557

Text #3

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.6404. Min Act: -0.0002

Data Index: 520732 (C4 (Web Text))

Max Activating Token Index: 266

Text #4

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.6733. Min Act: -0.0002

Data Index: 1056403 (C4 (Web Text))

Max Activating Token Index: 921

Text #5

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.6536. Min Act: -0.0002

Data Index: 978131 (C4 (Web Text))

Max Activating Token Index: 87

Text #6

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.6666. Min Act: -0.0002

Data Index: 617386 (C4 (Web Text))

Max Activating Token Index: 504

Text #7

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.6418. Min Act: -0.0002

Data Index: 167125 (C4 (Web Text))

Max Activating Token Index: 340

Text #8

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.6001. Min Act: -0.0002

Data Index: 261059 (C4 (Web Text))

Max Activating Token Index: 463

Text #9

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.6334. Min Act: -0.0002

Data Index: 182726 (C4 (Web Text))

Max Activating Token Index: 320

Text #10

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.5756. Min Act: -0.0002

Data Index: 18028 (C4 (Web Text))

Max Activating Token Index: 504

Text #11

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.5672. Min Act: -0.0002

Data Index: 79553 (C4 (Web Text))

Max Activating Token Index: 829

Text #12

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.5669. Min Act: -0.0002

Data Index: 708316 (C4 (Web Text))

Max Activating Token Index: 497

Text #13

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.5788. Min Act: -0.0002

Data Index: 526360 (C4 (Web Text))

Max Activating Token Index: 344

Text #14

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.5703. Min Act: -0.0002

Data Index: 424454 (C4 (Web Text))

Max Activating Token Index: 198

Text #15

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.5580. Min Act: -0.0002

Data Index: 1124650 (C4 (Web Text))

Max Activating Token Index: 853

Text #16

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.5398. Min Act: -0.0002

Data Index: 666914 (C4 (Web Text))

Max Activating Token Index: 572

Text #17

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.5264. Min Act: -0.0002

Data Index: 120473 (C4 (Web Text))

Max Activating Token Index: 313

Text #18

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.5210. Min Act: -0.0002

Data Index: 943950 (C4 (Web Text))

Max Activating Token Index: 796

Text #19

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.5334. Min Act: -0.0002

Data Index: 235121 (C4 (Web Text))

Max Activating Token Index: 391