Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2756 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.5289. Min Act: -0.0003

Data Index: 365636 (C4 (Web Text))

Max Activating Token Index: 260

Text #1

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.5465. Min Act: -0.0003

Data Index: 880591 (C4 (Web Text))

Max Activating Token Index: 248

Text #2

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.5556. Min Act: -0.0003

Data Index: 443161 (C4 (Web Text))

Max Activating Token Index: 512

Text #3

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.5547. Min Act: -0.0003

Data Index: 1205776 (C4 (Web Text))

Max Activating Token Index: 636

Text #4

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.5360. Min Act: -0.0003

Data Index: 290255 (C4 (Web Text))

Max Activating Token Index: 742

Text #5

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.4770. Min Act: -0.0003

Data Index: 566618 (C4 (Web Text))

Max Activating Token Index: 271

Text #6

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.5386. Min Act: -0.0003

Data Index: 979607 (C4 (Web Text))

Max Activating Token Index: 237

Text #7

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.5311. Min Act: -0.0003

Data Index: 197168 (C4 (Web Text))

Max Activating Token Index: 145

Text #8

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.4785. Min Act: -0.0003

Data Index: 347647 (C4 (Web Text))

Max Activating Token Index: 362

Text #9

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.4862. Min Act: -0.0003

Data Index: 423277 (C4 (Web Text))

Max Activating Token Index: 756

Text #10

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.4686. Min Act: -0.0003

Data Index: 938770 (C4 (Web Text))

Max Activating Token Index: 792

Text #11

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.4834. Min Act: -0.0003

Data Index: 1260658 (C4 (Web Text))

Max Activating Token Index: 381

Text #12

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.4809. Min Act: -0.0003

Data Index: 349545 (C4 (Web Text))

Max Activating Token Index: 88

Text #13

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.4960. Min Act: -0.0003

Data Index: 614532 (C4 (Web Text))

Max Activating Token Index: 271

Text #14

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.4801. Min Act: -0.0003

Data Index: 220294 (C4 (Web Text))

Max Activating Token Index: 196

Text #15

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.4919. Min Act: -0.0003

Data Index: 1278448 (C4 (Web Text))

Max Activating Token Index: 460

Text #16

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.5037. Min Act: -0.0003

Data Index: 226957 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.4572. Min Act: -0.0003

Data Index: 788349 (C4 (Web Text))

Max Activating Token Index: 673

Text #18

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.4773. Min Act: -0.0003

Data Index: 423064 (C4 (Web Text))

Max Activating Token Index: 512

Text #19

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.4343. Min Act: -0.0003

Data Index: 1198870 (C4 (Web Text))

Max Activating Token Index: 115