Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1599 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.7635. Min Act: -0.0001

Data Index: 26229 (C4 (Web Text))

Max Activating Token Index: 391

Text #1

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.7256. Min Act: -0.0000

Data Index: 816267 (C4 (Web Text))

Max Activating Token Index: 1005

Text #2

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.7019. Min Act: -0.0000

Data Index: 654494 (C4 (Web Text))

Max Activating Token Index: 668

Text #3

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.6889. Min Act: -0.0000

Data Index: 246749 (C4 (Web Text))

Max Activating Token Index: 622

Text #4

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.6470. Min Act: -0.0000

Data Index: 1108865 (C4 (Web Text))

Max Activating Token Index: 351

Text #5

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.5765. Min Act: -0.0000

Data Index: 865507 (C4 (Web Text))

Max Activating Token Index: 399

Text #6

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.5926. Min Act: -0.0001

Data Index: 961056 (C4 (Web Text))

Max Activating Token Index: 859

Text #7

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.5842. Min Act: -0.0000

Data Index: 1202276 (C4 (Web Text))

Max Activating Token Index: 1020

Text #8

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.5912. Min Act: -0.0000

Data Index: 704402 (C4 (Web Text))

Max Activating Token Index: 887

Text #9

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.5622. Min Act: -0.0001

Data Index: 600791 (C4 (Web Text))

Max Activating Token Index: 442

Text #10

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.5674. Min Act: -0.0001

Data Index: 164988 (C4 (Web Text))

Max Activating Token Index: 800

Text #11

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.5352. Min Act: -0.0000

Data Index: 847780 (C4 (Web Text))

Max Activating Token Index: 589

Text #12

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.5506. Min Act: -0.0000

Data Index: 615531 (C4 (Web Text))

Max Activating Token Index: 53

Text #13

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.5458. Min Act: -0.0000

Data Index: 1263503 (C4 (Web Text))

Max Activating Token Index: 265

Text #14

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.5397. Min Act: -0.0001

Data Index: 1067082 (C4 (Web Text))

Max Activating Token Index: 441

Text #15

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.5342. Min Act: -0.0000

Data Index: 583692 (C4 (Web Text))

Max Activating Token Index: 352

Text #16

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.5512. Min Act: -0.0000

Data Index: 945335 (C4 (Web Text))

Max Activating Token Index: 644

Text #17

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.5364. Min Act: -0.0001

Data Index: 1161869 (C4 (Web Text))

Max Activating Token Index: 705

Text #18

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.5428. Min Act: -0.0000

Data Index: 173441 (C4 (Web Text))

Max Activating Token Index: 708

Text #19

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.5284. Min Act: -0.0000

Data Index: 303866 (C4 (Web Text))

Max Activating Token Index: 803