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

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

Neuron 1300 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6192. Min Range: -0.6192

Max Act: 0.6192. Min Act: -0.0000

Data Index: 1402494 (Python Code)

Max Activating Token Index: 87

Text #1

Max Range: 0.6192. Min Range: -0.6192

Max Act: 0.5104. Min Act: -0.0000

Data Index: 1365262 (Python Code)

Max Activating Token Index: 532

Text #2

Max Range: 0.6192. Min Range: -0.6192

Max Act: 0.4588. Min Act: -0.0000

Data Index: 595132 (C4 (Web Text))

Max Activating Token Index: 264

Text #3

Max Range: 0.6192. Min Range: -0.6192

Max Act: 0.5129. Min Act: -0.0000

Data Index: 332510 (C4 (Web Text))

Max Activating Token Index: 144

Text #4

Max Range: 0.6192. Min Range: -0.6192

Max Act: 0.4764. Min Act: -0.0000

Data Index: 796682 (C4 (Web Text))

Max Activating Token Index: 376

Text #5

Max Range: 0.6192. Min Range: -0.6192

Max Act: 0.4035. Min Act: -0.0000

Data Index: 809250 (C4 (Web Text))

Max Activating Token Index: 663

Text #6

Max Range: 0.6192. Min Range: -0.6192

Max Act: 0.3544. Min Act: -0.0000

Data Index: 32234 (C4 (Web Text))

Max Activating Token Index: 803

Text #7

Max Range: 0.6192. Min Range: -0.6192

Max Act: 0.4124. Min Act: -0.0000

Data Index: 620099 (C4 (Web Text))

Max Activating Token Index: 767

Text #8

Max Range: 0.6192. Min Range: -0.6192

Max Act: 0.3845. Min Act: -0.0000

Data Index: 821337 (C4 (Web Text))

Max Activating Token Index: 665

Text #9

Max Range: 0.6192. Min Range: -0.6192

Max Act: 0.3508. Min Act: -0.0000

Data Index: 1548841 (Python Code)

Max Activating Token Index: 56

Text #10

Max Range: 0.6192. Min Range: -0.6192

Max Act: 0.3506. Min Act: -0.0000

Data Index: 1365129 (Python Code)

Max Activating Token Index: 959

Text #11

Max Range: 0.6192. Min Range: -0.6192

Max Act: 0.3161. Min Act: -0.0000

Data Index: 364766 (C4 (Web Text))

Max Activating Token Index: 756

Text #12

Max Range: 0.6192. Min Range: -0.6192

Max Act: 0.3595. Min Act: -0.0000

Data Index: 305800 (C4 (Web Text))

Max Activating Token Index: 394

Text #13

Max Range: 0.6192. Min Range: -0.6192

Max Act: 0.3471. Min Act: -0.0000

Data Index: 1643266 (Python Code)

Max Activating Token Index: 170

Text #14

Max Range: 0.6192. Min Range: -0.6192

Max Act: 0.3253. Min Act: -0.0000

Data Index: 1137184 (C4 (Web Text))

Max Activating Token Index: 439

Text #15

Max Range: 0.6192. Min Range: -0.6192

Max Act: 0.3430. Min Act: -0.0000

Data Index: 138169 (C4 (Web Text))

Max Activating Token Index: 170

Text #16

Max Range: 0.6192. Min Range: -0.6192

Max Act: 0.3329. Min Act: -0.0000

Data Index: 803384 (C4 (Web Text))

Max Activating Token Index: 63

Text #17

Max Range: 0.6192. Min Range: -0.6192

Max Act: 0.3339. Min Act: -0.0000

Data Index: 1438211 (Python Code)

Max Activating Token Index: 312

Text #18

Max Range: 0.6192. Min Range: -0.6192

Max Act: 0.3325. Min Act: -0.0000

Data Index: 858072 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 0.6192. Min Range: -0.6192

Max Act: 0.3283. Min Act: -0.0000

Data Index: 65417 (C4 (Web Text))

Max Activating Token Index: 602