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

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

Neuron 107 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.4720. Min Act: -0.0000

Data Index: 1582578 (Python Code)

Max Activating Token Index: 398

Text #1

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.4811. Min Act: -0.0000

Data Index: 1435935 (Python Code)

Max Activating Token Index: 367

Text #2

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.4457. Min Act: -0.0000

Data Index: 1402593 (Python Code)

Max Activating Token Index: 385

Text #3

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.4395. Min Act: -0.0000

Data Index: 1506619 (Python Code)

Max Activating Token Index: 217

Text #4

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.4456. Min Act: -0.0000

Data Index: 820894 (C4 (Web Text))

Max Activating Token Index: 342

Text #5

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.4091. Min Act: -0.0000

Data Index: 411656 (C4 (Web Text))

Max Activating Token Index: 434

Text #6

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.4128. Min Act: -0.0000

Data Index: 1359892 (Python Code)

Max Activating Token Index: 773

Text #7

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.3831. Min Act: -0.0000

Data Index: 782028 (C4 (Web Text))

Max Activating Token Index: 714

Text #8

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.3778. Min Act: -0.0000

Data Index: 669229 (C4 (Web Text))

Max Activating Token Index: 371

Text #9

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.3506. Min Act: -0.0000

Data Index: 932806 (C4 (Web Text))

Max Activating Token Index: 654

Text #10

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.3535. Min Act: -0.0000

Data Index: 629853 (C4 (Web Text))

Max Activating Token Index: 355

Text #11

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.3633. Min Act: -0.0000

Data Index: 556918 (C4 (Web Text))

Max Activating Token Index: 295

Text #12

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.3287. Min Act: -0.0000

Data Index: 534460 (C4 (Web Text))

Max Activating Token Index: 76

Text #13

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.3480. Min Act: -0.0000

Data Index: 1356825 (C4 (Web Text))

Max Activating Token Index: 759

Text #14

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.3491. Min Act: -0.0000

Data Index: 1467291 (Python Code)

Max Activating Token Index: 743

Text #15

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.3473. Min Act: -0.0000

Data Index: 566381 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.3458. Min Act: -0.0000

Data Index: 446339 (C4 (Web Text))

Max Activating Token Index: 272

Text #17

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.3443. Min Act: -0.0000

Data Index: 311704 (C4 (Web Text))

Max Activating Token Index: 446

Text #18

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.3303. Min Act: -0.0000

Data Index: 1646917 (Python Code)

Max Activating Token Index: 307

Text #19

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.3168. Min Act: -0.0000

Data Index: 411948 (C4 (Web Text))

Max Activating Token Index: 360