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

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

Neuron 3472 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.2308. Min Act: -0.0000

Data Index: 58384 (C4 (Web Text))

Max Activating Token Index: 666

Text #1

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.2495. Min Act: -0.0000

Data Index: 850184 (C4 (Web Text))

Max Activating Token Index: 1020

Text #2

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.2561. Min Act: -0.0000

Data Index: 571659 (C4 (Web Text))

Max Activating Token Index: 415

Text #3

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.2386. Min Act: -0.0000

Data Index: 335049 (C4 (Web Text))

Max Activating Token Index: 236

Text #4

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.2312. Min Act: -0.0000

Data Index: 868609 (C4 (Web Text))

Max Activating Token Index: 140

Text #5

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.2314. Min Act: -0.0000

Data Index: 519212 (C4 (Web Text))

Max Activating Token Index: 512

Text #6

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.2350. Min Act: -0.0000

Data Index: 1001667 (C4 (Web Text))

Max Activating Token Index: 956

Text #7

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.2134. Min Act: -0.0000

Data Index: 1176711 (C4 (Web Text))

Max Activating Token Index: 505

Text #8

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.1974. Min Act: -0.0000

Data Index: 831414 (C4 (Web Text))

Max Activating Token Index: 844

Text #9

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.2160. Min Act: -0.0000

Data Index: 957012 (C4 (Web Text))

Max Activating Token Index: 577

Text #10

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.2068. Min Act: -0.0000

Data Index: 330316 (C4 (Web Text))

Max Activating Token Index: 413

Text #11

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.2040. Min Act: -0.0000

Data Index: 19611 (C4 (Web Text))

Max Activating Token Index: 961

Text #12

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.1883. Min Act: -0.0000

Data Index: 757641 (C4 (Web Text))

Max Activating Token Index: 581

Text #13

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.1562. Min Act: -0.0000

Data Index: 705337 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.1605. Min Act: -0.0000

Data Index: 1357789 (C4 (Web Text))

Max Activating Token Index: 225

Text #15

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.1882. Min Act: -0.0000

Data Index: 926056 (C4 (Web Text))

Max Activating Token Index: 693

Text #16

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.1646. Min Act: -0.0000

Data Index: 835986 (C4 (Web Text))

Max Activating Token Index: 994

Text #17

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.1718. Min Act: -0.0000

Data Index: 128110 (C4 (Web Text))

Max Activating Token Index: 1015

Text #18

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.1906. Min Act: -0.0000

Data Index: 1006873 (C4 (Web Text))

Max Activating Token Index: 26

Text #19

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.1626. Min Act: -0.0000

Data Index: 988274 (C4 (Web Text))

Max Activating Token Index: 296