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

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

Neuron 1433 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.1764. Min Range: -1.1764

Max Act: 1.1764. Min Act: -0.0002

Data Index: 455384 (C4 (Web Text))

Max Activating Token Index: 667

Text #1

Max Range: 1.1764. Min Range: -1.1764

Max Act: 1.1470. Min Act: -0.0002

Data Index: 1646261 (Python Code)

Max Activating Token Index: 342

Text #2

Max Range: 1.1764. Min Range: -1.1764

Max Act: 1.1313. Min Act: -0.0002

Data Index: 1153337 (C4 (Web Text))

Max Activating Token Index: 355

Text #3

Max Range: 1.1764. Min Range: -1.1764

Max Act: 1.1083. Min Act: -0.0002

Data Index: 414407 (C4 (Web Text))

Max Activating Token Index: 459

Text #4

Max Range: 1.1764. Min Range: -1.1764

Max Act: 1.0875. Min Act: -0.0003

Data Index: 510969 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 1.1764. Min Range: -1.1764

Max Act: 1.0711. Min Act: -0.0002

Data Index: 324038 (C4 (Web Text))

Max Activating Token Index: 236

Text #6

Max Range: 1.1764. Min Range: -1.1764

Max Act: 1.0494. Min Act: -0.0002

Data Index: 279539 (C4 (Web Text))

Max Activating Token Index: 774

Text #7

Max Range: 1.1764. Min Range: -1.1764

Max Act: 1.0555. Min Act: -0.0002

Data Index: 967132 (C4 (Web Text))

Max Activating Token Index: 618

Text #8

Max Range: 1.1764. Min Range: -1.1764

Max Act: 1.0376. Min Act: -0.0002

Data Index: 1295102 (C4 (Web Text))

Max Activating Token Index: 279

Text #9

Max Range: 1.1764. Min Range: -1.1764

Max Act: 1.0207. Min Act: -0.0002

Data Index: 474461 (C4 (Web Text))

Max Activating Token Index: 449

Text #10

Max Range: 1.1764. Min Range: -1.1764

Max Act: 1.0380. Min Act: -0.0002

Data Index: 696642 (C4 (Web Text))

Max Activating Token Index: 426

Text #11

Max Range: 1.1764. Min Range: -1.1764

Max Act: 1.0118. Min Act: -0.0002

Data Index: 1142347 (C4 (Web Text))

Max Activating Token Index: 458

Text #12

Max Range: 1.1764. Min Range: -1.1764

Max Act: 1.0068. Min Act: -0.0002

Data Index: 504766 (C4 (Web Text))

Max Activating Token Index: 493

Text #13

Max Range: 1.1764. Min Range: -1.1764

Max Act: 1.0001. Min Act: -0.0002

Data Index: 49463 (C4 (Web Text))

Max Activating Token Index: 597

Text #14

Max Range: 1.1764. Min Range: -1.1764

Max Act: 0.9848. Min Act: -0.0002

Data Index: 1038505 (C4 (Web Text))

Max Activating Token Index: 469

Text #15

Max Range: 1.1764. Min Range: -1.1764

Max Act: 0.9595. Min Act: -0.0002

Data Index: 429520 (C4 (Web Text))

Max Activating Token Index: 291

Text #16

Max Range: 1.1764. Min Range: -1.1764

Max Act: 0.9771. Min Act: -0.0002

Data Index: 253528 (C4 (Web Text))

Max Activating Token Index: 1004

Text #17

Max Range: 1.1764. Min Range: -1.1764

Max Act: 0.9797. Min Act: -0.0003

Data Index: 482686 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 1.1764. Min Range: -1.1764

Max Act: 0.9787. Min Act: -0.0002

Data Index: 257222 (C4 (Web Text))

Max Activating Token Index: 751

Text #19

Max Range: 1.1764. Min Range: -1.1764

Max Act: 0.9753. Min Act: -0.0002

Data Index: 1211647 (C4 (Web Text))

Max Activating Token Index: 657