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

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

Neuron 1431 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: 1.3029. Min Range: -1.3029

Max Act: 1.3029. Min Act: -0.0000

Data Index: 317598 (C4 (Web Text))

Max Activating Token Index: 877

Text #1

Max Range: 1.3029. Min Range: -1.3029

Max Act: 1.2601. Min Act: -0.0000

Data Index: 1387191 (Python Code)

Max Activating Token Index: 731

Text #2

Max Range: 1.3029. Min Range: -1.3029

Max Act: 1.2753. Min Act: -0.0000

Data Index: 851202 (C4 (Web Text))

Max Activating Token Index: 783

Text #3

Max Range: 1.3029. Min Range: -1.3029

Max Act: 1.2810. Min Act: -0.0000

Data Index: 1366216 (Python Code)

Max Activating Token Index: 763

Text #4

Max Range: 1.3029. Min Range: -1.3029

Max Act: 1.2597. Min Act: -0.0001

Data Index: 1324522 (C4 (Web Text))

Max Activating Token Index: 309

Text #5

Max Range: 1.3029. Min Range: -1.3029

Max Act: 1.2864. Min Act: -0.0000

Data Index: 658983 (C4 (Web Text))

Max Activating Token Index: 496

Text #6

Max Range: 1.3029. Min Range: -1.3029

Max Act: 1.2364. Min Act: -0.0000

Data Index: 648811 (C4 (Web Text))

Max Activating Token Index: 381

Text #7

Max Range: 1.3029. Min Range: -1.3029

Max Act: 1.2370. Min Act: -0.0000

Data Index: 1654361 (Python Code)

Max Activating Token Index: 689

Text #8

Max Range: 1.3029. Min Range: -1.3029

Max Act: 1.2447. Min Act: -0.0000

Data Index: 1654458 (Python Code)

Max Activating Token Index: 845

Text #9

Max Range: 1.3029. Min Range: -1.3029

Max Act: 1.2062. Min Act: -0.0000

Data Index: 517289 (C4 (Web Text))

Max Activating Token Index: 657

Text #10

Max Range: 1.3029. Min Range: -1.3029

Max Act: 1.1994. Min Act: -0.0000

Data Index: 268445 (C4 (Web Text))

Max Activating Token Index: 539

Text #11

Max Range: 1.3029. Min Range: -1.3029

Max Act: 1.2211. Min Act: -0.0000

Data Index: 1428327 (Python Code)

Max Activating Token Index: 902

Text #12

Max Range: 1.3029. Min Range: -1.3029

Max Act: 1.1963. Min Act: -0.0000

Data Index: 1287792 (C4 (Web Text))

Max Activating Token Index: 160

Text #13

Max Range: 1.3029. Min Range: -1.3029

Max Act: 1.2585. Min Act: -0.0000

Data Index: 168690 (C4 (Web Text))

Max Activating Token Index: 149

Text #14

Max Range: 1.3029. Min Range: -1.3029

Max Act: 1.1638. Min Act: -0.0000

Data Index: 527422 (C4 (Web Text))

Max Activating Token Index: 908

Text #15

Max Range: 1.3029. Min Range: -1.3029

Max Act: 1.1603. Min Act: -0.0000

Data Index: 782864 (C4 (Web Text))

Max Activating Token Index: 901

Text #16

Max Range: 1.3029. Min Range: -1.3029

Max Act: 1.1582. Min Act: -0.0000

Data Index: 751767 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 1.3029. Min Range: -1.3029

Max Act: 1.1209. Min Act: -0.0000

Data Index: 1611914 (Python Code)

Max Activating Token Index: 865

Text #18

Max Range: 1.3029. Min Range: -1.3029

Max Act: 1.1872. Min Act: -0.0000

Data Index: 1634849 (Python Code)

Max Activating Token Index: 405

Text #19

Max Range: 1.3029. Min Range: -1.3029

Max Act: 1.1456. Min Act: -0.0001

Data Index: 1501281 (Python Code)

Max Activating Token Index: 644