Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 708 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.2338. Min Range: -1.2338

Max Act: 1.2338. Min Act: -0.0000

Data Index: 1575478 (The Pile)

Max Activating Token Index: 276

Text #1

Max Range: 1.2338. Min Range: -1.2338

Max Act: 1.1370. Min Act: -0.0000

Data Index: 712855 (The Pile)

Max Activating Token Index: 209

Text #2

Max Range: 1.2338. Min Range: -1.2338

Max Act: 1.2010. Min Act: -0.0000

Data Index: 1877494 (The Pile)

Max Activating Token Index: 208

Text #3

Max Range: 1.2338. Min Range: -1.2338

Max Act: 1.0811. Min Act: -0.0000

Data Index: 141282 (The Pile)

Max Activating Token Index: 712

Text #4

Max Range: 1.2338. Min Range: -1.2338

Max Act: 1.1502. Min Act: -0.0000

Data Index: 1745568 (The Pile)

Max Activating Token Index: 580

Text #5

Max Range: 1.2338. Min Range: -1.2338

Max Act: 1.0417. Min Act: -0.0000

Data Index: 1305995 (The Pile)

Max Activating Token Index: 428

Text #6

Max Range: 1.2338. Min Range: -1.2338

Max Act: 1.0971. Min Act: -0.0000

Data Index: 1987481 (The Pile)

Max Activating Token Index: 721

Text #7

Max Range: 1.2338. Min Range: -1.2338

Max Act: 1.1011. Min Act: -0.0000

Data Index: 305220 (The Pile)

Max Activating Token Index: 543

Text #8

Max Range: 1.2338. Min Range: -1.2338

Max Act: 1.0743. Min Act: -0.0000

Data Index: 1179403 (The Pile)

Max Activating Token Index: 436

Text #9

Max Range: 1.2338. Min Range: -1.2338

Max Act: 1.1069. Min Act: -0.0000

Data Index: 632867 (The Pile)

Max Activating Token Index: 135

Text #10

Max Range: 1.2338. Min Range: -1.2338

Max Act: 1.1177. Min Act: -0.0000

Data Index: 1214028 (The Pile)

Max Activating Token Index: 175

Text #11

Max Range: 1.2338. Min Range: -1.2338

Max Act: 1.0751. Min Act: -0.0000

Data Index: 999719 (The Pile)

Max Activating Token Index: 393

Text #12

Max Range: 1.2338. Min Range: -1.2338

Max Act: 1.0695. Min Act: -0.0000

Data Index: 960901 (The Pile)

Max Activating Token Index: 158

Text #13

Max Range: 1.2338. Min Range: -1.2338

Max Act: 1.0257. Min Act: -0.0000

Data Index: 1803416 (The Pile)

Max Activating Token Index: 398

Text #14

Max Range: 1.2338. Min Range: -1.2338

Max Act: 1.0506. Min Act: -0.0000

Data Index: 1447207 (The Pile)

Max Activating Token Index: 705

Text #15

Max Range: 1.2338. Min Range: -1.2338

Max Act: 1.0197. Min Act: -0.0000

Data Index: 1429291 (The Pile)

Max Activating Token Index: 770

Text #16

Max Range: 1.2338. Min Range: -1.2338

Max Act: 1.0101. Min Act: -0.0000

Data Index: 1582816 (The Pile)

Max Activating Token Index: 713

Text #17

Max Range: 1.2338. Min Range: -1.2338

Max Act: 0.9762. Min Act: -0.0000

Data Index: 810124 (The Pile)

Max Activating Token Index: 797

Text #18

Max Range: 1.2338. Min Range: -1.2338

Max Act: 1.0560. Min Act: -0.0000

Data Index: 419930 (The Pile)

Max Activating Token Index: 1006

Text #19

Max Range: 1.2338. Min Range: -1.2338

Max Act: 0.9853. Min Act: -0.0000

Data Index: 848537 (The Pile)

Max Activating Token Index: 364