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

Dataset: The Pile

Neuron 1862 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.3060. Min Act: -0.0000

Data Index: 1541930 (The Pile)

Max Activating Token Index: 962

Text #1

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.2472. Min Act: -0.0000

Data Index: 1577540 (The Pile)

Max Activating Token Index: 383

Text #2

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.2019. Min Act: -0.0000

Data Index: 1090451 (The Pile)

Max Activating Token Index: 362

Text #3

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.1894. Min Act: -0.0000

Data Index: 774435 (The Pile)

Max Activating Token Index: 122

Text #4

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.2026. Min Act: -0.0000

Data Index: 1935900 (The Pile)

Max Activating Token Index: 834

Text #5

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.1951. Min Act: -0.0000

Data Index: 28849 (The Pile)

Max Activating Token Index: 263

Text #6

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.1628. Min Act: -0.0000

Data Index: 55939 (The Pile)

Max Activating Token Index: 923

Text #7

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.1700. Min Act: -0.0000

Data Index: 68772 (The Pile)

Max Activating Token Index: 97

Text #8

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.1513. Min Act: -0.0000

Data Index: 310012 (The Pile)

Max Activating Token Index: 79

Text #9

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.1464. Min Act: -0.0000

Data Index: 1053356 (The Pile)

Max Activating Token Index: 835

Text #10

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.1498. Min Act: -0.0000

Data Index: 1241828 (The Pile)

Max Activating Token Index: 143

Text #11

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.1378. Min Act: -0.0000

Data Index: 1265472 (The Pile)

Max Activating Token Index: 764

Text #12

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.1418. Min Act: -0.0000

Data Index: 1370313 (The Pile)

Max Activating Token Index: 1000

Text #13

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.1386. Min Act: -0.0000

Data Index: 279655 (The Pile)

Max Activating Token Index: 228

Text #14

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.1379. Min Act: -0.0000

Data Index: 635223 (The Pile)

Max Activating Token Index: 273

Text #15

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.1387. Min Act: -0.0000

Data Index: 1760984 (The Pile)

Max Activating Token Index: 399

Text #16

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.1324. Min Act: -0.0000

Data Index: 1206523 (The Pile)

Max Activating Token Index: 539

Text #17

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.1437. Min Act: -0.0000

Data Index: 1272263 (The Pile)

Max Activating Token Index: 853

Text #18

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.1412. Min Act: -0.0000

Data Index: 1669372 (The Pile)

Max Activating Token Index: 17

Text #19

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.1377. Min Act: -0.0000

Data Index: 550753 (The Pile)

Max Activating Token Index: 708