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

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

Neuron 2439 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0622. Min Range: -5.0622

Max Act: 5.0622. Min Act: -0.0000

Data Index: 1187626 (C4 (Web Text))

Max Activating Token Index: 716

Text #1

Max Range: 5.0622. Min Range: -5.0622

Max Act: 4.8828. Min Act: -0.0000

Data Index: 863621 (C4 (Web Text))

Max Activating Token Index: 737

Text #2

Max Range: 5.0622. Min Range: -5.0622

Max Act: 3.9894. Min Act: -0.0000

Data Index: 805583 (C4 (Web Text))

Max Activating Token Index: 402

Text #3

Max Range: 5.0622. Min Range: -5.0622

Max Act: 4.1273. Min Act: -0.0000

Data Index: 539825 (C4 (Web Text))

Max Activating Token Index: 521

Text #4

Max Range: 5.0622. Min Range: -5.0622

Max Act: 3.3473. Min Act: -0.0000

Data Index: 408511 (C4 (Web Text))

Max Activating Token Index: 840

Text #5

Max Range: 5.0622. Min Range: -5.0622

Max Act: 3.2852. Min Act: -0.0000

Data Index: 77612 (C4 (Web Text))

Max Activating Token Index: 162

Text #6

Max Range: 5.0622. Min Range: -5.0622

Max Act: 3.1285. Min Act: -0.0000

Data Index: 1551319 (Python Code)

Max Activating Token Index: 868

Text #7

Max Range: 5.0622. Min Range: -5.0622

Max Act: 3.5194. Min Act: -0.0000

Data Index: 494523 (C4 (Web Text))

Max Activating Token Index: 498

Text #8

Max Range: 5.0622. Min Range: -5.0622

Max Act: 3.1483. Min Act: -0.0000

Data Index: 1240573 (C4 (Web Text))

Max Activating Token Index: 303

Text #9

Max Range: 5.0622. Min Range: -5.0622

Max Act: 3.0767. Min Act: -0.0000

Data Index: 100997 (C4 (Web Text))

Max Activating Token Index: 941

Text #10

Max Range: 5.0622. Min Range: -5.0622

Max Act: 3.3777. Min Act: -0.0000

Data Index: 907544 (C4 (Web Text))

Max Activating Token Index: 40

Text #11

Max Range: 5.0622. Min Range: -5.0622

Max Act: 3.0370. Min Act: -0.0000

Data Index: 614654 (C4 (Web Text))

Max Activating Token Index: 84

Text #12

Max Range: 5.0622. Min Range: -5.0622

Max Act: 3.0001. Min Act: -0.0000

Data Index: 936177 (C4 (Web Text))

Max Activating Token Index: 738

Text #13

Max Range: 5.0622. Min Range: -5.0622

Max Act: 2.9933. Min Act: -0.0000

Data Index: 1319464 (C4 (Web Text))

Max Activating Token Index: 459

Text #14

Max Range: 5.0622. Min Range: -5.0622

Max Act: 3.1182. Min Act: -0.0000

Data Index: 448402 (C4 (Web Text))

Max Activating Token Index: 555

Text #15

Max Range: 5.0622. Min Range: -5.0622

Max Act: 3.1176. Min Act: -0.0000

Data Index: 1449520 (Python Code)

Max Activating Token Index: 101

Text #16

Max Range: 5.0622. Min Range: -5.0622

Max Act: 2.9566. Min Act: -0.0000

Data Index: 711741 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 5.0622. Min Range: -5.0622

Max Act: 2.8432. Min Act: -0.0000

Data Index: 1051255 (C4 (Web Text))

Max Activating Token Index: 101

Text #18

Max Range: 5.0622. Min Range: -5.0622

Max Act: 2.8180. Min Act: -0.0000

Data Index: 593287 (C4 (Web Text))

Max Activating Token Index: 272

Text #19

Max Range: 5.0622. Min Range: -5.0622

Max Act: 2.9051. Min Act: -0.0000

Data Index: 29632 (C4 (Web Text))

Max Activating Token Index: 266