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

Dataset: The Pile

Neuron 154 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: 1.8368. Min Range: -1.8368

Max Act: 1.8368. Min Act: -0.0000

Data Index: 1302293 (The Pile)

Max Activating Token Index: 881

Text #1

Max Range: 1.8368. Min Range: -1.8368

Max Act: 1.7072. Min Act: -0.0000

Data Index: 1059096 (The Pile)

Max Activating Token Index: 757

Text #2

Max Range: 1.8368. Min Range: -1.8368

Max Act: 1.6743. Min Act: -0.0000

Data Index: 469459 (The Pile)

Max Activating Token Index: 282

Text #3

Max Range: 1.8368. Min Range: -1.8368

Max Act: 1.7530. Min Act: -0.0000

Data Index: 263823 (The Pile)

Max Activating Token Index: 899

Text #4

Max Range: 1.8368. Min Range: -1.8368

Max Act: 1.7348. Min Act: -0.0000

Data Index: 1490699 (The Pile)

Max Activating Token Index: 1015

Text #5

Max Range: 1.8368. Min Range: -1.8368

Max Act: 1.5303. Min Act: -0.0000

Data Index: 859973 (The Pile)

Max Activating Token Index: 409

Text #6

Max Range: 1.8368. Min Range: -1.8368

Max Act: 1.6929. Min Act: -0.0000

Data Index: 1194879 (The Pile)

Max Activating Token Index: 916

Text #7

Max Range: 1.8368. Min Range: -1.8368

Max Act: 1.4311. Min Act: -0.0000

Data Index: 835270 (The Pile)

Max Activating Token Index: 993

Text #8

Max Range: 1.8368. Min Range: -1.8368

Max Act: 1.5670. Min Act: -0.0000

Data Index: 835200 (The Pile)

Max Activating Token Index: 500

Text #9

Max Range: 1.8368. Min Range: -1.8368

Max Act: 1.4866. Min Act: -0.0000

Data Index: 709453 (The Pile)

Max Activating Token Index: 433

Text #10

Max Range: 1.8368. Min Range: -1.8368

Max Act: 1.4424. Min Act: -0.0000

Data Index: 487761 (The Pile)

Max Activating Token Index: 401

Text #11

Max Range: 1.8368. Min Range: -1.8368

Max Act: 1.5363. Min Act: -0.0000

Data Index: 1425501 (The Pile)

Max Activating Token Index: 631

Text #12

Max Range: 1.8368. Min Range: -1.8368

Max Act: 1.5364. Min Act: -0.0000

Data Index: 537442 (The Pile)

Max Activating Token Index: 893

Text #13

Max Range: 1.8368. Min Range: -1.8368

Max Act: 1.5407. Min Act: -0.0000

Data Index: 933470 (The Pile)

Max Activating Token Index: 901

Text #14

Max Range: 1.8368. Min Range: -1.8368

Max Act: 1.6260. Min Act: -0.0000

Data Index: 377295 (The Pile)

Max Activating Token Index: 276

Text #15

Max Range: 1.8368. Min Range: -1.8368

Max Act: 1.4339. Min Act: -0.0000

Data Index: 974013 (The Pile)

Max Activating Token Index: 737

Text #16

Max Range: 1.8368. Min Range: -1.8368

Max Act: 1.4439. Min Act: -0.0000

Data Index: 127839 (The Pile)

Max Activating Token Index: 967

Text #17

Max Range: 1.8368. Min Range: -1.8368

Max Act: 1.5240. Min Act: -0.0000

Data Index: 1109020 (The Pile)

Max Activating Token Index: 419

Text #18

Max Range: 1.8368. Min Range: -1.8368

Max Act: 1.5139. Min Act: -0.0000

Data Index: 1732520 (The Pile)

Max Activating Token Index: 868

Text #19

Max Range: 1.8368. Min Range: -1.8368

Max Act: 1.5029. Min Act: -0.0000

Data Index: 590882 (The Pile)

Max Activating Token Index: 883