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

Dataset: The Pile

Neuron 2677 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: 0.8063. Min Range: -0.8063

Max Act: 0.8063. Min Act: -0.0000

Data Index: 1430915 (The Pile)

Max Activating Token Index: 718

Text #1

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.7717. Min Act: -0.0000

Data Index: 200793 (The Pile)

Max Activating Token Index: 464

Text #2

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.6862. Min Act: -0.0000

Data Index: 456039 (The Pile)

Max Activating Token Index: 418

Text #3

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.7150. Min Act: -0.0000

Data Index: 1051816 (The Pile)

Max Activating Token Index: 1010

Text #4

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.7051. Min Act: -0.0000

Data Index: 186004 (The Pile)

Max Activating Token Index: 447

Text #5

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.6797. Min Act: -0.0000

Data Index: 1415641 (The Pile)

Max Activating Token Index: 431

Text #6

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.6164. Min Act: -0.0000

Data Index: 791485 (The Pile)

Max Activating Token Index: 980

Text #7

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.7230. Min Act: -0.0000

Data Index: 902746 (The Pile)

Max Activating Token Index: 584

Text #8

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.6502. Min Act: -0.0000

Data Index: 1921225 (The Pile)

Max Activating Token Index: 609

Text #9

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.6351. Min Act: -0.0000

Data Index: 451028 (The Pile)

Max Activating Token Index: 77

Text #10

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.6435. Min Act: -0.0000

Data Index: 102261 (The Pile)

Max Activating Token Index: 222

Text #11

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.6229. Min Act: -0.0000

Data Index: 1267559 (The Pile)

Max Activating Token Index: 73

Text #12

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.6001. Min Act: -0.0000

Data Index: 1485182 (The Pile)

Max Activating Token Index: 590

Text #13

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.5801. Min Act: -0.0000

Data Index: 1602337 (The Pile)

Max Activating Token Index: 637

Text #14

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.5795. Min Act: -0.0000

Data Index: 1800005 (The Pile)

Max Activating Token Index: 137

Text #15

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.6284. Min Act: -0.0000

Data Index: 207923 (The Pile)

Max Activating Token Index: 104

Text #16

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.5433. Min Act: -0.0000

Data Index: 514536 (The Pile)

Max Activating Token Index: 673

Text #17

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.5906. Min Act: -0.0000

Data Index: 882319 (The Pile)

Max Activating Token Index: 484

Text #18

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.5555. Min Act: -0.0000

Data Index: 273084 (The Pile)

Max Activating Token Index: 904

Text #19

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.5297. Min Act: -0.0000

Data Index: 393491 (The Pile)

Max Activating Token Index: 975