Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3362 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.7900. Min Range: -1.7900

Max Act: 1.7033. Min Act: -0.0000

Data Index: 1175762 (C4 (Web Text))

Max Activating Token Index: 596

Text #1

Max Range: 1.7900. Min Range: -1.7900

Max Act: 1.7900. Min Act: -0.0000

Data Index: 434437 (C4 (Web Text))

Max Activating Token Index: 470

Text #2

Max Range: 1.7900. Min Range: -1.7900

Max Act: 1.6782. Min Act: -0.0000

Data Index: 42269 (C4 (Web Text))

Max Activating Token Index: 473

Text #3

Max Range: 1.7900. Min Range: -1.7900

Max Act: 1.6044. Min Act: -0.0000

Data Index: 1466600 (Python Code)

Max Activating Token Index: 257

Text #4

Max Range: 1.7900. Min Range: -1.7900

Max Act: 1.5850. Min Act: -0.0000

Data Index: 1370344 (Python Code)

Max Activating Token Index: 331

Text #5

Max Range: 1.7900. Min Range: -1.7900

Max Act: 1.5465. Min Act: -0.0000

Data Index: 1438568 (Python Code)

Max Activating Token Index: 79

Text #6

Max Range: 1.7900. Min Range: -1.7900

Max Act: 1.5032. Min Act: -0.0000

Data Index: 1427190 (Python Code)

Max Activating Token Index: 366

Text #7

Max Range: 1.7900. Min Range: -1.7900

Max Act: 1.4293. Min Act: -0.0000

Data Index: 940574 (C4 (Web Text))

Max Activating Token Index: 289

Text #8

Max Range: 1.7900. Min Range: -1.7900

Max Act: 1.4681. Min Act: -0.0000

Data Index: 1434174 (Python Code)

Max Activating Token Index: 1020

Text #9

Max Range: 1.7900. Min Range: -1.7900

Max Act: 1.3370. Min Act: -0.0000

Data Index: 1542583 (Python Code)

Max Activating Token Index: 475

Text #10

Max Range: 1.7900. Min Range: -1.7900

Max Act: 1.4533. Min Act: -0.0000

Data Index: 1312468 (C4 (Web Text))

Max Activating Token Index: 371

Text #11

Max Range: 1.7900. Min Range: -1.7900

Max Act: 1.3498. Min Act: -0.0000

Data Index: 1587152 (Python Code)

Max Activating Token Index: 823

Text #12

Max Range: 1.7900. Min Range: -1.7900

Max Act: 1.4252. Min Act: -0.0000

Data Index: 1510372 (Python Code)

Max Activating Token Index: 491

Text #13

Max Range: 1.7900. Min Range: -1.7900

Max Act: 1.3190. Min Act: -0.0000

Data Index: 1575441 (Python Code)

Max Activating Token Index: 772

Text #14

Max Range: 1.7900. Min Range: -1.7900

Max Act: 1.3535. Min Act: -0.0000

Data Index: 1366814 (Python Code)

Max Activating Token Index: 265

Text #15

Max Range: 1.7900. Min Range: -1.7900

Max Act: 1.3384. Min Act: -0.0000

Data Index: 1371073 (Python Code)

Max Activating Token Index: 572

Text #16

Max Range: 1.7900. Min Range: -1.7900

Max Act: 1.3431. Min Act: -0.0000

Data Index: 1547265 (Python Code)

Max Activating Token Index: 684

Text #17

Max Range: 1.7900. Min Range: -1.7900

Max Act: 1.3269. Min Act: -0.0000

Data Index: 1375930 (Python Code)

Max Activating Token Index: 455

Text #18

Max Range: 1.7900. Min Range: -1.7900

Max Act: 1.3239. Min Act: -0.0000

Data Index: 1446106 (Python Code)

Max Activating Token Index: 499

Text #19

Max Range: 1.7900. Min Range: -1.7900

Max Act: 1.2644. Min Act: -0.0000

Data Index: 1466005 (Python Code)

Max Activating Token Index: 342