Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3492 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6365. Min Range: -0.6365

Max Act: 0.6365. Min Act: -0.0000

Data Index: 741444 (C4 (Web Text))

Max Activating Token Index: 468

Text #1

Max Range: 0.6365. Min Range: -0.6365

Max Act: 0.5926. Min Act: -0.0000

Data Index: 9676 (C4 (Web Text))

Max Activating Token Index: 753

Text #2

Max Range: 0.6365. Min Range: -0.6365

Max Act: 0.5800. Min Act: -0.0000

Data Index: 926826 (C4 (Web Text))

Max Activating Token Index: 705

Text #3

Max Range: 0.6365. Min Range: -0.6365

Max Act: 0.4981. Min Act: -0.0000

Data Index: 545218 (C4 (Web Text))

Max Activating Token Index: 824

Text #4

Max Range: 0.6365. Min Range: -0.6365

Max Act: 0.5414. Min Act: -0.0000

Data Index: 167159 (C4 (Web Text))

Max Activating Token Index: 129

Text #5

Max Range: 0.6365. Min Range: -0.6365

Max Act: 0.5426. Min Act: -0.0000

Data Index: 1347523 (C4 (Web Text))

Max Activating Token Index: 916

Text #6

Max Range: 0.6365. Min Range: -0.6365

Max Act: 0.5253. Min Act: -0.0000

Data Index: 967466 (C4 (Web Text))

Max Activating Token Index: 458

Text #7

Max Range: 0.6365. Min Range: -0.6365

Max Act: 0.5719. Min Act: -0.0000

Data Index: 929073 (C4 (Web Text))

Max Activating Token Index: 958

Text #8

Max Range: 0.6365. Min Range: -0.6365

Max Act: 0.4360. Min Act: -0.0000

Data Index: 1542508 (Python Code)

Max Activating Token Index: 730

Text #9

Max Range: 0.6365. Min Range: -0.6365

Max Act: 0.4867. Min Act: -0.0000

Data Index: 97042 (C4 (Web Text))

Max Activating Token Index: 244

Text #10

Max Range: 0.6365. Min Range: -0.6365

Max Act: 0.5380. Min Act: -0.0000

Data Index: 1191327 (C4 (Web Text))

Max Activating Token Index: 896

Text #11

Max Range: 0.6365. Min Range: -0.6365

Max Act: 0.5331. Min Act: -0.0000

Data Index: 166856 (C4 (Web Text))

Max Activating Token Index: 724

Text #12

Max Range: 0.6365. Min Range: -0.6365

Max Act: 0.4723. Min Act: -0.0000

Data Index: 388537 (C4 (Web Text))

Max Activating Token Index: 830

Text #13

Max Range: 0.6365. Min Range: -0.6365

Max Act: 0.4606. Min Act: -0.0000

Data Index: 1300099 (C4 (Web Text))

Max Activating Token Index: 494

Text #14

Max Range: 0.6365. Min Range: -0.6365

Max Act: 0.4634. Min Act: -0.0000

Data Index: 941307 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 0.6365. Min Range: -0.6365

Max Act: 0.4530. Min Act: -0.0000

Data Index: 987861 (C4 (Web Text))

Max Activating Token Index: 363

Text #16

Max Range: 0.6365. Min Range: -0.6365

Max Act: 0.4804. Min Act: -0.0000

Data Index: 355197 (C4 (Web Text))

Max Activating Token Index: 287

Text #17

Max Range: 0.6365. Min Range: -0.6365

Max Act: 0.4412. Min Act: -0.0000

Data Index: 1324784 (C4 (Web Text))

Max Activating Token Index: 465

Text #18

Max Range: 0.6365. Min Range: -0.6365

Max Act: 0.4700. Min Act: -0.0000

Data Index: 1105788 (C4 (Web Text))

Max Activating Token Index: 202

Text #19

Max Range: 0.6365. Min Range: -0.6365

Max Act: 0.3652. Min Act: -0.0000

Data Index: 1012558 (C4 (Web Text))

Max Activating Token Index: 752