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

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

Neuron 5520 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2894. Min Range: -3.2894

Max Act: 3.2894. Min Act: -0.0001

Data Index: 899267 (C4 (Web Text))

Max Activating Token Index: 484

Text #1

Max Range: 3.2894. Min Range: -3.2894

Max Act: 3.1287. Min Act: -0.0001

Data Index: 921290 (C4 (Web Text))

Max Activating Token Index: 538

Text #2

Max Range: 3.2894. Min Range: -3.2894

Max Act: 2.7390. Min Act: -0.0001

Data Index: 1356591 (C4 (Web Text))

Max Activating Token Index: 404

Text #3

Max Range: 3.2894. Min Range: -3.2894

Max Act: 3.1770. Min Act: -0.0000

Data Index: 1554266 (Python Code)

Max Activating Token Index: 291

Text #4

Max Range: 3.2894. Min Range: -3.2894

Max Act: 3.0215. Min Act: -0.0001

Data Index: 131973 (C4 (Web Text))

Max Activating Token Index: 581

Text #5

Max Range: 3.2894. Min Range: -3.2894

Max Act: 3.0158. Min Act: -0.0001

Data Index: 479562 (C4 (Web Text))

Max Activating Token Index: 751

Text #6

Max Range: 3.2894. Min Range: -3.2894

Max Act: 2.7690. Min Act: -0.0001

Data Index: 423700 (C4 (Web Text))

Max Activating Token Index: 854

Text #7

Max Range: 3.2894. Min Range: -3.2894

Max Act: 3.2729. Min Act: -0.0001

Data Index: 303853 (C4 (Web Text))

Max Activating Token Index: 219

Text #8

Max Range: 3.2894. Min Range: -3.2894

Max Act: 3.0129. Min Act: -0.0001

Data Index: 1577056 (Python Code)

Max Activating Token Index: 398

Text #9

Max Range: 3.2894. Min Range: -3.2894

Max Act: 3.2787. Min Act: -0.0001

Data Index: 464411 (C4 (Web Text))

Max Activating Token Index: 224

Text #10

Max Range: 3.2894. Min Range: -3.2894

Max Act: 2.9753. Min Act: -0.0001

Data Index: 988208 (C4 (Web Text))

Max Activating Token Index: 467

Text #11

Max Range: 3.2894. Min Range: -3.2894

Max Act: 2.8605. Min Act: -0.0001

Data Index: 90036 (C4 (Web Text))

Max Activating Token Index: 422

Text #12

Max Range: 3.2894. Min Range: -3.2894

Max Act: 2.7242. Min Act: -0.0001

Data Index: 771929 (C4 (Web Text))

Max Activating Token Index: 307

Text #13

Max Range: 3.2894. Min Range: -3.2894

Max Act: 2.9688. Min Act: -0.0000

Data Index: 471022 (C4 (Web Text))

Max Activating Token Index: 280

Text #14

Max Range: 3.2894. Min Range: -3.2894

Max Act: 2.7653. Min Act: -0.0001

Data Index: 1608490 (Python Code)

Max Activating Token Index: 632

Text #15

Max Range: 3.2894. Min Range: -3.2894

Max Act: 3.0382. Min Act: -0.0000

Data Index: 1590410 (Python Code)

Max Activating Token Index: 512

Text #16

Max Range: 3.2894. Min Range: -3.2894

Max Act: 2.5650. Min Act: -0.0001

Data Index: 1574258 (Python Code)

Max Activating Token Index: 242

Text #17

Max Range: 3.2894. Min Range: -3.2894

Max Act: 2.6302. Min Act: -0.0001

Data Index: 140314 (C4 (Web Text))

Max Activating Token Index: 911

Text #18

Max Range: 3.2894. Min Range: -3.2894

Max Act: 2.5524. Min Act: -0.0000

Data Index: 1636482 (Python Code)

Max Activating Token Index: 353

Text #19

Max Range: 3.2894. Min Range: -3.2894

Max Act: 2.5776. Min Act: -0.0001

Data Index: 1562775 (Python Code)

Max Activating Token Index: 393