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

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

Neuron 1222 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6660. Min Range: -2.6660

Max Act: 2.6660. Min Act: -0.0001

Data Index: 1578210 (Python Code)

Max Activating Token Index: 762

Text #1

Max Range: 2.6660. Min Range: -2.6660

Max Act: 2.4201. Min Act: -0.0000

Data Index: 1584417 (Python Code)

Max Activating Token Index: 603

Text #2

Max Range: 2.6660. Min Range: -2.6660

Max Act: 2.3549. Min Act: -0.0000

Data Index: 1432495 (Python Code)

Max Activating Token Index: 503

Text #3

Max Range: 2.6660. Min Range: -2.6660

Max Act: 2.3162. Min Act: -0.0000

Data Index: 1447782 (Python Code)

Max Activating Token Index: 161

Text #4

Max Range: 2.6660. Min Range: -2.6660

Max Act: 2.2578. Min Act: -0.0000

Data Index: 644765 (C4 (Web Text))

Max Activating Token Index: 52

Text #5

Max Range: 2.6660. Min Range: -2.6660

Max Act: 2.2495. Min Act: -0.0000

Data Index: 1642647 (Python Code)

Max Activating Token Index: 688

Text #6

Max Range: 2.6660. Min Range: -2.6660

Max Act: 2.1520. Min Act: -0.0000

Data Index: 127211 (C4 (Web Text))

Max Activating Token Index: 908

Text #7

Max Range: 2.6660. Min Range: -2.6660

Max Act: 2.2228. Min Act: -0.0000

Data Index: 342941 (C4 (Web Text))

Max Activating Token Index: 836

Text #8

Max Range: 2.6660. Min Range: -2.6660

Max Act: 1.9225. Min Act: -0.0000

Data Index: 1166249 (C4 (Web Text))

Max Activating Token Index: 724

Text #9

Max Range: 2.6660. Min Range: -2.6660

Max Act: 2.1716. Min Act: -0.0000

Data Index: 1403712 (Python Code)

Max Activating Token Index: 14

Text #10

Max Range: 2.6660. Min Range: -2.6660

Max Act: 2.0141. Min Act: -0.0001

Data Index: 968424 (C4 (Web Text))

Max Activating Token Index: 872

Text #11

Max Range: 2.6660. Min Range: -2.6660

Max Act: 2.0561. Min Act: -0.0000

Data Index: 273139 (C4 (Web Text))

Max Activating Token Index: 90

Text #12

Max Range: 2.6660. Min Range: -2.6660

Max Act: 1.9518. Min Act: -0.0000

Data Index: 361303 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 2.6660. Min Range: -2.6660

Max Act: 1.8568. Min Act: -0.0000

Data Index: 394277 (C4 (Web Text))

Max Activating Token Index: 618

Text #14

Max Range: 2.6660. Min Range: -2.6660

Max Act: 2.0485. Min Act: -0.0000

Data Index: 737539 (C4 (Web Text))

Max Activating Token Index: 297

Text #15

Max Range: 2.6660. Min Range: -2.6660

Max Act: 2.1113. Min Act: -0.0000

Data Index: 1185731 (C4 (Web Text))

Max Activating Token Index: 680

Text #16

Max Range: 2.6660. Min Range: -2.6660

Max Act: 2.0242. Min Act: -0.0000

Data Index: 60448 (C4 (Web Text))

Max Activating Token Index: 109

Text #17

Max Range: 2.6660. Min Range: -2.6660

Max Act: 1.9953. Min Act: -0.0000

Data Index: 1601917 (Python Code)

Max Activating Token Index: 783

Text #18

Max Range: 2.6660. Min Range: -2.6660

Max Act: 1.7990. Min Act: -0.0000

Data Index: 383205 (C4 (Web Text))

Max Activating Token Index: 958

Text #19

Max Range: 2.6660. Min Range: -2.6660

Max Act: 2.0067. Min Act: -0.0000

Data Index: 1464512 (Python Code)

Max Activating Token Index: 30