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

Dataset: The Pile

Neuron 1245 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.8014. Min Act: -0.0000

Data Index: 1066568 (The Pile)

Max Activating Token Index: 699

Text #1

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.7739. Min Act: -0.0000

Data Index: 1330190 (The Pile)

Max Activating Token Index: 206

Text #2

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.7361. Min Act: -0.0000

Data Index: 1248159 (The Pile)

Max Activating Token Index: 425

Text #3

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.6627. Min Act: -0.0000

Data Index: 554343 (The Pile)

Max Activating Token Index: 539

Text #4

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.7323. Min Act: -0.0000

Data Index: 1871179 (The Pile)

Max Activating Token Index: 341

Text #5

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.6431. Min Act: -0.0000

Data Index: 1333681 (The Pile)

Max Activating Token Index: 885

Text #6

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.6763. Min Act: -0.0000

Data Index: 602935 (The Pile)

Max Activating Token Index: 444

Text #7

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.5462. Min Act: -0.0000

Data Index: 1089045 (The Pile)

Max Activating Token Index: 896

Text #8

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.6201. Min Act: -0.0000

Data Index: 1469153 (The Pile)

Max Activating Token Index: 215

Text #9

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.6369. Min Act: -0.0000

Data Index: 173168 (The Pile)

Max Activating Token Index: 35

Text #10

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.6523. Min Act: -0.0000

Data Index: 897363 (The Pile)

Max Activating Token Index: 396

Text #11

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.6362. Min Act: -0.0000

Data Index: 1056389 (The Pile)

Max Activating Token Index: 382

Text #12

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.6376. Min Act: -0.0000

Data Index: 48723 (The Pile)

Max Activating Token Index: 171

Text #13

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.6410. Min Act: -0.0000

Data Index: 477500 (The Pile)

Max Activating Token Index: 829

Text #14

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.5610. Min Act: -0.0000

Data Index: 1947385 (The Pile)

Max Activating Token Index: 827

Text #15

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.6039. Min Act: -0.0000

Data Index: 880909 (The Pile)

Max Activating Token Index: 921

Text #16

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.6093. Min Act: -0.0000

Data Index: 621176 (The Pile)

Max Activating Token Index: 551

Text #17

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.5964. Min Act: -0.0000

Data Index: 464484 (The Pile)

Max Activating Token Index: 813

Text #18

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.5972. Min Act: -0.0000

Data Index: 764642 (The Pile)

Max Activating Token Index: 657

Text #19

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.5896. Min Act: -0.0000

Data Index: 1264817 (The Pile)

Max Activating Token Index: 972