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

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

Neuron 769 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: 3.1700. Min Range: -3.1700

Max Act: 3.1265. Min Act: -0.0000

Data Index: 6718 (C4 (Web Text))

Max Activating Token Index: 614

Text #1

Max Range: 3.1700. Min Range: -3.1700

Max Act: 3.1700. Min Act: -0.0001

Data Index: 903569 (C4 (Web Text))

Max Activating Token Index: 372

Text #2

Max Range: 3.1700. Min Range: -3.1700

Max Act: 2.8007. Min Act: -0.0000

Data Index: 194078 (C4 (Web Text))

Max Activating Token Index: 911

Text #3

Max Range: 3.1700. Min Range: -3.1700

Max Act: 2.8234. Min Act: -0.0000

Data Index: 1124635 (C4 (Web Text))

Max Activating Token Index: 770

Text #4

Max Range: 3.1700. Min Range: -3.1700

Max Act: 2.5120. Min Act: -0.0000

Data Index: 1060475 (C4 (Web Text))

Max Activating Token Index: 141

Text #5

Max Range: 3.1700. Min Range: -3.1700

Max Act: 2.6228. Min Act: -0.0001

Data Index: 613594 (C4 (Web Text))

Max Activating Token Index: 346

Text #6

Max Range: 3.1700. Min Range: -3.1700

Max Act: 2.4800. Min Act: -0.0001

Data Index: 1060757 (C4 (Web Text))

Max Activating Token Index: 381

Text #7

Max Range: 3.1700. Min Range: -3.1700

Max Act: 2.5425. Min Act: -0.0001

Data Index: 337977 (C4 (Web Text))

Max Activating Token Index: 93

Text #8

Max Range: 3.1700. Min Range: -3.1700

Max Act: 2.4832. Min Act: -0.0001

Data Index: 134575 (C4 (Web Text))

Max Activating Token Index: 511

Text #9

Max Range: 3.1700. Min Range: -3.1700

Max Act: 2.4603. Min Act: -0.0001

Data Index: 1273398 (C4 (Web Text))

Max Activating Token Index: 278

Text #10

Max Range: 3.1700. Min Range: -3.1700

Max Act: 2.1371. Min Act: -0.0001

Data Index: 533402 (C4 (Web Text))

Max Activating Token Index: 720

Text #11

Max Range: 3.1700. Min Range: -3.1700

Max Act: 2.5972. Min Act: -0.0001

Data Index: 248861 (C4 (Web Text))

Max Activating Token Index: 1021

Text #12

Max Range: 3.1700. Min Range: -3.1700

Max Act: 2.2039. Min Act: -0.0001

Data Index: 1269475 (C4 (Web Text))

Max Activating Token Index: 709

Text #13

Max Range: 3.1700. Min Range: -3.1700

Max Act: 2.3025. Min Act: -0.0001

Data Index: 853126 (C4 (Web Text))

Max Activating Token Index: 662

Text #14

Max Range: 3.1700. Min Range: -3.1700

Max Act: 2.1904. Min Act: -0.0001

Data Index: 252508 (C4 (Web Text))

Max Activating Token Index: 583

Text #15

Max Range: 3.1700. Min Range: -3.1700

Max Act: 2.2799. Min Act: -0.0001

Data Index: 464132 (C4 (Web Text))

Max Activating Token Index: 768

Text #16

Max Range: 3.1700. Min Range: -3.1700

Max Act: 2.2985. Min Act: -0.0001

Data Index: 1100651 (C4 (Web Text))

Max Activating Token Index: 718

Text #17

Max Range: 3.1700. Min Range: -3.1700

Max Act: 2.1698. Min Act: -0.0001

Data Index: 529540 (C4 (Web Text))

Max Activating Token Index: 816

Text #18

Max Range: 3.1700. Min Range: -3.1700

Max Act: 2.4003. Min Act: -0.0001

Data Index: 106713 (C4 (Web Text))

Max Activating Token Index: 568

Text #19

Max Range: 3.1700. Min Range: -3.1700

Max Act: 2.1576. Min Act: -0.0001

Data Index: 958142 (C4 (Web Text))

Max Activating Token Index: 390