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

Dataset: The Pile

Neuron 2355 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.3685. Min Act: -0.0000

Data Index: 1239780 (The Pile)

Max Activating Token Index: 838

Text #1

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.3459. Min Act: -0.0000

Data Index: 47702 (The Pile)

Max Activating Token Index: 308

Text #2

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.3442. Min Act: -0.0000

Data Index: 1928500 (The Pile)

Max Activating Token Index: 982

Text #3

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.3526. Min Act: -0.0000

Data Index: 1895342 (The Pile)

Max Activating Token Index: 678

Text #4

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.3444. Min Act: -0.0000

Data Index: 1626299 (The Pile)

Max Activating Token Index: 266

Text #5

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.3261. Min Act: 0.0000

Data Index: 1303804 (The Pile)

Max Activating Token Index: 992

Text #6

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.3150. Min Act: -0.0000

Data Index: 288568 (The Pile)

Max Activating Token Index: 496

Text #7

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.3095. Min Act: 0.0000

Data Index: 856332 (The Pile)

Max Activating Token Index: 1014

Text #8

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.3094. Min Act: 0.0000

Data Index: 1893996 (The Pile)

Max Activating Token Index: 712

Text #9

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.3013. Min Act: 0.0000

Data Index: 1288104 (The Pile)

Max Activating Token Index: 406

Text #10

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.3041. Min Act: -0.0000

Data Index: 1871734 (The Pile)

Max Activating Token Index: 463

Text #11

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.3100. Min Act: -0.0000

Data Index: 474428 (The Pile)

Max Activating Token Index: 169

Text #12

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.2792. Min Act: -0.0000

Data Index: 127147 (The Pile)

Max Activating Token Index: 791

Text #13

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.2919. Min Act: -0.0000

Data Index: 1554301 (The Pile)

Max Activating Token Index: 536

Text #14

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.3060. Min Act: -0.0000

Data Index: 1415789 (The Pile)

Max Activating Token Index: 213

Text #15

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.2867. Min Act: -0.0000

Data Index: 774194 (The Pile)

Max Activating Token Index: 968

Text #16

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.2966. Min Act: -0.0000

Data Index: 144270 (The Pile)

Max Activating Token Index: 358

Text #17

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.2670. Min Act: 0.0000

Data Index: 1703677 (The Pile)

Max Activating Token Index: 582

Text #18

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.2902. Min Act: -0.0000

Data Index: 1070050 (The Pile)

Max Activating Token Index: 826

Text #19

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.2607. Min Act: -0.0000

Data Index: 59084 (The Pile)

Max Activating Token Index: 729