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

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

Neuron 2581 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: 2.9330. Min Range: -2.9330

Max Act: 2.9330. Min Act: -0.0000

Data Index: 67482 (C4 (Web Text))

Max Activating Token Index: 775

Text #1

Max Range: 2.9330. Min Range: -2.9330

Max Act: 2.4406. Min Act: -0.0000

Data Index: 857233 (C4 (Web Text))

Max Activating Token Index: 684

Text #2

Max Range: 2.9330. Min Range: -2.9330

Max Act: 2.6271. Min Act: -0.0000

Data Index: 262141 (C4 (Web Text))

Max Activating Token Index: 781

Text #3

Max Range: 2.9330. Min Range: -2.9330

Max Act: 2.3337. Min Act: -0.0000

Data Index: 613118 (C4 (Web Text))

Max Activating Token Index: 400

Text #4

Max Range: 2.9330. Min Range: -2.9330

Max Act: 2.6862. Min Act: -0.0000

Data Index: 219842 (C4 (Web Text))

Max Activating Token Index: 283

Text #5

Max Range: 2.9330. Min Range: -2.9330

Max Act: 2.6534. Min Act: -0.0000

Data Index: 1137415 (C4 (Web Text))

Max Activating Token Index: 388

Text #6

Max Range: 2.9330. Min Range: -2.9330

Max Act: 2.6077. Min Act: -0.0000

Data Index: 531170 (C4 (Web Text))

Max Activating Token Index: 133

Text #7

Max Range: 2.9330. Min Range: -2.9330

Max Act: 2.5220. Min Act: -0.0000

Data Index: 993058 (C4 (Web Text))

Max Activating Token Index: 856

Text #8

Max Range: 2.9330. Min Range: -2.9330

Max Act: 2.7247. Min Act: -0.0000

Data Index: 845974 (C4 (Web Text))

Max Activating Token Index: 295

Text #9

Max Range: 2.9330. Min Range: -2.9330

Max Act: 2.3317. Min Act: -0.0000

Data Index: 1124448 (C4 (Web Text))

Max Activating Token Index: 861

Text #10

Max Range: 2.9330. Min Range: -2.9330

Max Act: 2.4394. Min Act: -0.0000

Data Index: 222756 (C4 (Web Text))

Max Activating Token Index: 25

Text #11

Max Range: 2.9330. Min Range: -2.9330

Max Act: 2.5630. Min Act: -0.0000

Data Index: 1351477 (C4 (Web Text))

Max Activating Token Index: 822

Text #12

Max Range: 2.9330. Min Range: -2.9330

Max Act: 2.5262. Min Act: -0.0000

Data Index: 68506 (C4 (Web Text))

Max Activating Token Index: 109

Text #13

Max Range: 2.9330. Min Range: -2.9330

Max Act: 2.0525. Min Act: -0.0000

Data Index: 881890 (C4 (Web Text))

Max Activating Token Index: 242

Text #14

Max Range: 2.9330. Min Range: -2.9330

Max Act: 2.4166. Min Act: -0.0001

Data Index: 143560 (C4 (Web Text))

Max Activating Token Index: 335

Text #15

Max Range: 2.9330. Min Range: -2.9330

Max Act: 2.3009. Min Act: -0.0001

Data Index: 573690 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 2.9330. Min Range: -2.9330

Max Act: 2.4784. Min Act: -0.0000

Data Index: 140455 (C4 (Web Text))

Max Activating Token Index: 776

Text #17

Max Range: 2.9330. Min Range: -2.9330

Max Act: 2.3644. Min Act: -0.0000

Data Index: 153611 (C4 (Web Text))

Max Activating Token Index: 556

Text #18

Max Range: 2.9330. Min Range: -2.9330

Max Act: 2.5661. Min Act: -0.0000

Data Index: 542317 (C4 (Web Text))

Max Activating Token Index: 846

Text #19

Max Range: 2.9330. Min Range: -2.9330

Max Act: 2.6450. Min Act: -0.0000

Data Index: 748869 (C4 (Web Text))

Max Activating Token Index: 531