Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3728 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.5038. Min Range: -3.5038

Max Act: 3.5038. Min Act: -0.0000

Data Index: 472030 (C4 (Web Text))

Max Activating Token Index: 664

Text #1

Max Range: 3.5038. Min Range: -3.5038

Max Act: 3.4520. Min Act: -0.0000

Data Index: 123927 (C4 (Web Text))

Max Activating Token Index: 124

Text #2

Max Range: 3.5038. Min Range: -3.5038

Max Act: 3.1937. Min Act: -0.0000

Data Index: 417217 (C4 (Web Text))

Max Activating Token Index: 93

Text #3

Max Range: 3.5038. Min Range: -3.5038

Max Act: 3.3218. Min Act: -0.0000

Data Index: 1164851 (C4 (Web Text))

Max Activating Token Index: 937

Text #4

Max Range: 3.5038. Min Range: -3.5038

Max Act: 3.2545. Min Act: -0.0000

Data Index: 852886 (C4 (Web Text))

Max Activating Token Index: 809

Text #5

Max Range: 3.5038. Min Range: -3.5038

Max Act: 2.8515. Min Act: -0.0000

Data Index: 167176 (C4 (Web Text))

Max Activating Token Index: 801

Text #6

Max Range: 3.5038. Min Range: -3.5038

Max Act: 2.9389. Min Act: -0.0000

Data Index: 1062255 (C4 (Web Text))

Max Activating Token Index: 569

Text #7

Max Range: 3.5038. Min Range: -3.5038

Max Act: 3.2266. Min Act: -0.0000

Data Index: 298756 (C4 (Web Text))

Max Activating Token Index: 589

Text #8

Max Range: 3.5038. Min Range: -3.5038

Max Act: 3.2255. Min Act: -0.0001

Data Index: 108055 (C4 (Web Text))

Max Activating Token Index: 36

Text #9

Max Range: 3.5038. Min Range: -3.5038

Max Act: 3.2487. Min Act: -0.0001

Data Index: 246152 (C4 (Web Text))

Max Activating Token Index: 412

Text #10

Max Range: 3.5038. Min Range: -3.5038

Max Act: 2.9404. Min Act: -0.0000

Data Index: 1100009 (C4 (Web Text))

Max Activating Token Index: 846

Text #11

Max Range: 3.5038. Min Range: -3.5038

Max Act: 3.0577. Min Act: -0.0001

Data Index: 1098281 (C4 (Web Text))

Max Activating Token Index: 402

Text #12

Max Range: 3.5038. Min Range: -3.5038

Max Act: 3.0479. Min Act: -0.0000

Data Index: 315915 (C4 (Web Text))

Max Activating Token Index: 716

Text #13

Max Range: 3.5038. Min Range: -3.5038

Max Act: 2.8846. Min Act: -0.0000

Data Index: 383494 (C4 (Web Text))

Max Activating Token Index: 487

Text #14

Max Range: 3.5038. Min Range: -3.5038

Max Act: 3.0190. Min Act: -0.0001

Data Index: 598682 (C4 (Web Text))

Max Activating Token Index: 68

Text #15

Max Range: 3.5038. Min Range: -3.5038

Max Act: 3.1428. Min Act: -0.0001

Data Index: 1295708 (C4 (Web Text))

Max Activating Token Index: 79

Text #16

Max Range: 3.5038. Min Range: -3.5038

Max Act: 2.6091. Min Act: -0.0000

Data Index: 1243189 (C4 (Web Text))

Max Activating Token Index: 294

Text #17

Max Range: 3.5038. Min Range: -3.5038

Max Act: 3.0273. Min Act: -0.0000

Data Index: 827649 (C4 (Web Text))

Max Activating Token Index: 383

Text #18

Max Range: 3.5038. Min Range: -3.5038

Max Act: 2.8619. Min Act: -0.0000

Data Index: 431325 (C4 (Web Text))

Max Activating Token Index: 404

Text #19

Max Range: 3.5038. Min Range: -3.5038

Max Act: 2.7778. Min Act: -0.0000

Data Index: 878654 (C4 (Web Text))

Max Activating Token Index: 777