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

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

Neuron 3480 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: 0.2750. Min Range: -0.2750

Max Act: 0.2746. Min Act: -0.0002

Data Index: 577256 (C4 (Web Text))

Max Activating Token Index: 763

Text #1

Max Range: 0.2750. Min Range: -0.2750

Max Act: 0.2750. Min Act: -0.0002

Data Index: 274797 (C4 (Web Text))

Max Activating Token Index: 320

Text #2

Max Range: 0.2750. Min Range: -0.2750

Max Act: 0.2724. Min Act: -0.0002

Data Index: 104713 (C4 (Web Text))

Max Activating Token Index: 539

Text #3

Max Range: 0.2750. Min Range: -0.2750

Max Act: 0.2667. Min Act: -0.0002

Data Index: 1234841 (C4 (Web Text))

Max Activating Token Index: 475

Text #4

Max Range: 0.2750. Min Range: -0.2750

Max Act: 0.2600. Min Act: -0.0002

Data Index: 489925 (C4 (Web Text))

Max Activating Token Index: 626

Text #5

Max Range: 0.2750. Min Range: -0.2750

Max Act: 0.2560. Min Act: -0.0002

Data Index: 1306042 (C4 (Web Text))

Max Activating Token Index: 301

Text #6

Max Range: 0.2750. Min Range: -0.2750

Max Act: 0.2487. Min Act: -0.0002

Data Index: 648011 (C4 (Web Text))

Max Activating Token Index: 538

Text #7

Max Range: 0.2750. Min Range: -0.2750

Max Act: 0.2534. Min Act: -0.0002

Data Index: 44046 (C4 (Web Text))

Max Activating Token Index: 316

Text #8

Max Range: 0.2750. Min Range: -0.2750

Max Act: 0.2561. Min Act: -0.0002

Data Index: 960439 (C4 (Web Text))

Max Activating Token Index: 133

Text #9

Max Range: 0.2750. Min Range: -0.2750

Max Act: 0.2487. Min Act: -0.0002

Data Index: 485232 (C4 (Web Text))

Max Activating Token Index: 525

Text #10

Max Range: 0.2750. Min Range: -0.2750

Max Act: 0.2493. Min Act: -0.0002

Data Index: 1312409 (C4 (Web Text))

Max Activating Token Index: 182

Text #11

Max Range: 0.2750. Min Range: -0.2750

Max Act: 0.2453. Min Act: -0.0002

Data Index: 68758 (C4 (Web Text))

Max Activating Token Index: 430

Text #12

Max Range: 0.2750. Min Range: -0.2750

Max Act: 0.2507. Min Act: -0.0002

Data Index: 677718 (C4 (Web Text))

Max Activating Token Index: 632

Text #13

Max Range: 0.2750. Min Range: -0.2750

Max Act: 0.2439. Min Act: -0.0003

Data Index: 16898 (C4 (Web Text))

Max Activating Token Index: 349

Text #14

Max Range: 0.2750. Min Range: -0.2750

Max Act: 0.2479. Min Act: -0.0002

Data Index: 944325 (C4 (Web Text))

Max Activating Token Index: 653

Text #15

Max Range: 0.2750. Min Range: -0.2750

Max Act: 0.2465. Min Act: -0.0002

Data Index: 427458 (C4 (Web Text))

Max Activating Token Index: 304

Text #16

Max Range: 0.2750. Min Range: -0.2750

Max Act: 0.2440. Min Act: -0.0002

Data Index: 1195659 (C4 (Web Text))

Max Activating Token Index: 429

Text #17

Max Range: 0.2750. Min Range: -0.2750

Max Act: 0.2450. Min Act: -0.0002

Data Index: 60037 (C4 (Web Text))

Max Activating Token Index: 432

Text #18

Max Range: 0.2750. Min Range: -0.2750

Max Act: 0.2495. Min Act: -0.0002

Data Index: 546771 (C4 (Web Text))

Max Activating Token Index: 98

Text #19

Max Range: 0.2750. Min Range: -0.2750

Max Act: 0.2454. Min Act: -0.0002

Data Index: 890378 (C4 (Web Text))

Max Activating Token Index: 396