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

Dataset: The Pile

Neuron 3277 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: 1.0984. Min Range: -1.0984

Max Act: 1.0572. Min Act: -0.0000

Data Index: 1147147 (The Pile)

Max Activating Token Index: 797

Text #1

Max Range: 1.0984. Min Range: -1.0984

Max Act: 1.0313. Min Act: -0.0000

Data Index: 404042 (The Pile)

Max Activating Token Index: 466

Text #2

Max Range: 1.0984. Min Range: -1.0984

Max Act: 1.0984. Min Act: -0.0000

Data Index: 1228802 (The Pile)

Max Activating Token Index: 583

Text #3

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.9973. Min Act: -0.0000

Data Index: 113541 (The Pile)

Max Activating Token Index: 263

Text #4

Max Range: 1.0984. Min Range: -1.0984

Max Act: 1.0869. Min Act: -0.0000

Data Index: 1556009 (The Pile)

Max Activating Token Index: 749

Text #5

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.9390. Min Act: -0.0000

Data Index: 223818 (The Pile)

Max Activating Token Index: 641

Text #6

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.9911. Min Act: -0.0000

Data Index: 1131124 (The Pile)

Max Activating Token Index: 492

Text #7

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.9911. Min Act: -0.0000

Data Index: 1967496 (The Pile)

Max Activating Token Index: 747

Text #8

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.8904. Min Act: -0.0000

Data Index: 1252431 (The Pile)

Max Activating Token Index: 499

Text #9

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.9731. Min Act: -0.0000

Data Index: 790226 (The Pile)

Max Activating Token Index: 602

Text #10

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.9661. Min Act: -0.0000

Data Index: 1352283 (The Pile)

Max Activating Token Index: 857

Text #11

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.8724. Min Act: -0.0000

Data Index: 524904 (The Pile)

Max Activating Token Index: 926

Text #12

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.9060. Min Act: -0.0000

Data Index: 1181882 (The Pile)

Max Activating Token Index: 489

Text #13

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.9147. Min Act: -0.0000

Data Index: 1558131 (The Pile)

Max Activating Token Index: 1009

Text #14

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.8450. Min Act: -0.0000

Data Index: 1448789 (The Pile)

Max Activating Token Index: 984

Text #15

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.8821. Min Act: -0.0000

Data Index: 1962101 (The Pile)

Max Activating Token Index: 316

Text #16

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.8492. Min Act: -0.0000

Data Index: 1586956 (The Pile)

Max Activating Token Index: 462

Text #17

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.9091. Min Act: -0.0000

Data Index: 1500466 (The Pile)

Max Activating Token Index: 975

Text #18

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.8378. Min Act: -0.0000

Data Index: 1600926 (The Pile)

Max Activating Token Index: 26

Text #19

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.8522. Min Act: -0.0000

Data Index: 704491 (The Pile)

Max Activating Token Index: 174