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

Dataset: The Pile

Neuron 1919 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: 0.1157. Min Range: -0.1157

Max Act: 0.1054. Min Act: -0.0000

Data Index: 109802 (The Pile)

Max Activating Token Index: 334

Text #1

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1055. Min Act: -0.0000

Data Index: 887800 (The Pile)

Max Activating Token Index: 29

Text #2

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1157. Min Act: -0.0000

Data Index: 658264 (The Pile)

Max Activating Token Index: 508

Text #3

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0976. Min Act: -0.0000

Data Index: 22009 (The Pile)

Max Activating Token Index: 591

Text #4

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0916. Min Act: -0.0000

Data Index: 1569839 (The Pile)

Max Activating Token Index: 214

Text #5

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1021. Min Act: -0.0000

Data Index: 1718312 (The Pile)

Max Activating Token Index: 281

Text #6

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0965. Min Act: -0.0000

Data Index: 662002 (The Pile)

Max Activating Token Index: 832

Text #7

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1011. Min Act: -0.0000

Data Index: 1513503 (The Pile)

Max Activating Token Index: 395

Text #8

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0969. Min Act: -0.0000

Data Index: 705501 (The Pile)

Max Activating Token Index: 386

Text #9

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0920. Min Act: -0.0000

Data Index: 188066 (The Pile)

Max Activating Token Index: 443

Text #10

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0988. Min Act: -0.0000

Data Index: 1684766 (The Pile)

Max Activating Token Index: 434

Text #11

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1012. Min Act: -0.0000

Data Index: 1478677 (The Pile)

Max Activating Token Index: 624

Text #12

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0925. Min Act: -0.0000

Data Index: 1847917 (The Pile)

Max Activating Token Index: 67

Text #13

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0872. Min Act: -0.0000

Data Index: 1240249 (The Pile)

Max Activating Token Index: 401

Text #14

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0903. Min Act: -0.0000

Data Index: 1825395 (The Pile)

Max Activating Token Index: 393

Text #15

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0921. Min Act: -0.0000

Data Index: 501466 (The Pile)

Max Activating Token Index: 589

Text #16

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0730. Min Act: -0.0000

Data Index: 1031945 (The Pile)

Max Activating Token Index: 639

Text #17

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0874. Min Act: -0.0000

Data Index: 1090488 (The Pile)

Max Activating Token Index: 242

Text #18

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0844. Min Act: -0.0000

Data Index: 1734597 (The Pile)

Max Activating Token Index: 60

Text #19

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0954. Min Act: -0.0000

Data Index: 1074392 (The Pile)

Max Activating Token Index: 723