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

Dataset: The Pile

Neuron 5116 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: 1.4158. Min Range: -1.4158

Max Act: 1.3414. Min Act: -0.0000

Data Index: 453729 (The Pile)

Max Activating Token Index: 717

Text #1

Max Range: 1.4158. Min Range: -1.4158

Max Act: 1.3414. Min Act: -0.0000

Data Index: 544432 (The Pile)

Max Activating Token Index: 360

Text #2

Max Range: 1.4158. Min Range: -1.4158

Max Act: 1.2557. Min Act: -0.0000

Data Index: 825901 (The Pile)

Max Activating Token Index: 984

Text #3

Max Range: 1.4158. Min Range: -1.4158

Max Act: 1.2577. Min Act: -0.0000

Data Index: 1435326 (The Pile)

Max Activating Token Index: 712

Text #4

Max Range: 1.4158. Min Range: -1.4158

Max Act: 1.4158. Min Act: -0.0000

Data Index: 1377219 (The Pile)

Max Activating Token Index: 1015

Text #5

Max Range: 1.4158. Min Range: -1.4158

Max Act: 1.2753. Min Act: -0.0000

Data Index: 135086 (The Pile)

Max Activating Token Index: 437

Text #6

Max Range: 1.4158. Min Range: -1.4158

Max Act: 1.2665. Min Act: -0.0000

Data Index: 1960055 (The Pile)

Max Activating Token Index: 45

Text #7

Max Range: 1.4158. Min Range: -1.4158

Max Act: 1.2789. Min Act: -0.0000

Data Index: 962625 (The Pile)

Max Activating Token Index: 589

Text #8

Max Range: 1.4158. Min Range: -1.4158

Max Act: 1.1810. Min Act: -0.0000

Data Index: 1402359 (The Pile)

Max Activating Token Index: 975

Text #9

Max Range: 1.4158. Min Range: -1.4158

Max Act: 1.2388. Min Act: -0.0000

Data Index: 30218 (The Pile)

Max Activating Token Index: 961

Text #10

Max Range: 1.4158. Min Range: -1.4158

Max Act: 1.2023. Min Act: -0.0000

Data Index: 1902127 (The Pile)

Max Activating Token Index: 650

Text #11

Max Range: 1.4158. Min Range: -1.4158

Max Act: 1.1919. Min Act: -0.0000

Data Index: 375277 (The Pile)

Max Activating Token Index: 935

Text #12

Max Range: 1.4158. Min Range: -1.4158

Max Act: 1.0370. Min Act: -0.0000

Data Index: 784031 (The Pile)

Max Activating Token Index: 166

Text #13

Max Range: 1.4158. Min Range: -1.4158

Max Act: 1.0906. Min Act: -0.0000

Data Index: 1883745 (The Pile)

Max Activating Token Index: 619

Text #14

Max Range: 1.4158. Min Range: -1.4158

Max Act: 1.1734. Min Act: -0.0000

Data Index: 405579 (The Pile)

Max Activating Token Index: 315

Text #15

Max Range: 1.4158. Min Range: -1.4158

Max Act: 1.2061. Min Act: -0.0000

Data Index: 1961159 (The Pile)

Max Activating Token Index: 822

Text #16

Max Range: 1.4158. Min Range: -1.4158

Max Act: 1.1338. Min Act: -0.0000

Data Index: 1030346 (The Pile)

Max Activating Token Index: 96

Text #17

Max Range: 1.4158. Min Range: -1.4158

Max Act: 1.0592. Min Act: -0.0000

Data Index: 1000443 (The Pile)

Max Activating Token Index: 222

Text #18

Max Range: 1.4158. Min Range: -1.4158

Max Act: 1.1980. Min Act: -0.0000

Data Index: 1205183 (The Pile)

Max Activating Token Index: 651

Text #19

Max Range: 1.4158. Min Range: -1.4158

Max Act: 1.1716. Min Act: -0.0000

Data Index: 940479 (The Pile)

Max Activating Token Index: 113