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

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

Neuron 2360 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2624. Min Range: -0.2624

Max Act: 0.2473. Min Act: -0.0000

Data Index: 1542795 (Python Code)

Max Activating Token Index: 776

Text #1

Max Range: 0.2624. Min Range: -0.2624

Max Act: 0.2624. Min Act: -0.0000

Data Index: 1443447 (Python Code)

Max Activating Token Index: 680

Text #2

Max Range: 0.2624. Min Range: -0.2624

Max Act: 0.2418. Min Act: -0.0000

Data Index: 1478851 (Python Code)

Max Activating Token Index: 549

Text #3

Max Range: 0.2624. Min Range: -0.2624

Max Act: 0.2285. Min Act: -0.0000

Data Index: 605371 (C4 (Web Text))

Max Activating Token Index: 977

Text #4

Max Range: 0.2624. Min Range: -0.2624

Max Act: 0.2281. Min Act: -0.0000

Data Index: 1196209 (C4 (Web Text))

Max Activating Token Index: 749

Text #5

Max Range: 0.2624. Min Range: -0.2624

Max Act: 0.2147. Min Act: -0.0000

Data Index: 222496 (C4 (Web Text))

Max Activating Token Index: 546

Text #6

Max Range: 0.2624. Min Range: -0.2624

Max Act: 0.2305. Min Act: -0.0000

Data Index: 1654528 (Python Code)

Max Activating Token Index: 211

Text #7

Max Range: 0.2624. Min Range: -0.2624

Max Act: 0.2223. Min Act: -0.0000

Data Index: 599901 (C4 (Web Text))

Max Activating Token Index: 855

Text #8

Max Range: 0.2624. Min Range: -0.2624

Max Act: 0.2209. Min Act: -0.0000

Data Index: 619481 (C4 (Web Text))

Max Activating Token Index: 1018

Text #9

Max Range: 0.2624. Min Range: -0.2624

Max Act: 0.2244. Min Act: -0.0000

Data Index: 1426459 (Python Code)

Max Activating Token Index: 540

Text #10

Max Range: 0.2624. Min Range: -0.2624

Max Act: 0.1887. Min Act: -0.0000

Data Index: 32435 (C4 (Web Text))

Max Activating Token Index: 763

Text #11

Max Range: 0.2624. Min Range: -0.2624

Max Act: 0.2238. Min Act: -0.0000

Data Index: 1006277 (C4 (Web Text))

Max Activating Token Index: 891

Text #12

Max Range: 0.2624. Min Range: -0.2624

Max Act: 0.2163. Min Act: -0.0000

Data Index: 183419 (C4 (Web Text))

Max Activating Token Index: 344

Text #13

Max Range: 0.2624. Min Range: -0.2624

Max Act: 0.2158. Min Act: -0.0000

Data Index: 1653820 (Python Code)

Max Activating Token Index: 723

Text #14

Max Range: 0.2624. Min Range: -0.2624

Max Act: 0.1996. Min Act: -0.0000

Data Index: 663522 (C4 (Web Text))

Max Activating Token Index: 406

Text #15

Max Range: 0.2624. Min Range: -0.2624

Max Act: 0.2021. Min Act: -0.0000

Data Index: 353788 (C4 (Web Text))

Max Activating Token Index: 517

Text #16

Max Range: 0.2624. Min Range: -0.2624

Max Act: 0.1866. Min Act: -0.0000

Data Index: 972211 (C4 (Web Text))

Max Activating Token Index: 632

Text #17

Max Range: 0.2624. Min Range: -0.2624

Max Act: 0.1882. Min Act: -0.0000

Data Index: 60168 (C4 (Web Text))

Max Activating Token Index: 352

Text #18

Max Range: 0.2624. Min Range: -0.2624

Max Act: 0.2170. Min Act: -0.0000

Data Index: 1307689 (C4 (Web Text))

Max Activating Token Index: 534

Text #19

Max Range: 0.2624. Min Range: -0.2624

Max Act: 0.2125. Min Act: -0.0000

Data Index: 314747 (C4 (Web Text))

Max Activating Token Index: 669