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

Dataset: The Pile

Neuron 291 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5795. Min Range: -0.5795

Max Act: 0.5662. Min Act: -0.0000

Data Index: 321648 (The Pile)

Max Activating Token Index: 86

Text #1

Max Range: 0.5795. Min Range: -0.5795

Max Act: 0.5517. Min Act: -0.0000

Data Index: 350652 (The Pile)

Max Activating Token Index: 943

Text #2

Max Range: 0.5795. Min Range: -0.5795

Max Act: 0.5795. Min Act: -0.0000

Data Index: 470944 (The Pile)

Max Activating Token Index: 111

Text #3

Max Range: 0.5795. Min Range: -0.5795

Max Act: 0.5229. Min Act: -0.0000

Data Index: 151104 (The Pile)

Max Activating Token Index: 895

Text #4

Max Range: 0.5795. Min Range: -0.5795

Max Act: 0.4270. Min Act: -0.0000

Data Index: 681041 (The Pile)

Max Activating Token Index: 936

Text #5

Max Range: 0.5795. Min Range: -0.5795

Max Act: 0.4099. Min Act: -0.0000

Data Index: 270534 (The Pile)

Max Activating Token Index: 495

Text #6

Max Range: 0.5795. Min Range: -0.5795

Max Act: 0.4214. Min Act: -0.0000

Data Index: 711970 (The Pile)

Max Activating Token Index: 496

Text #7

Max Range: 0.5795. Min Range: -0.5795

Max Act: 0.4046. Min Act: -0.0000

Data Index: 1624287 (The Pile)

Max Activating Token Index: 255

Text #8

Max Range: 0.5795. Min Range: -0.5795

Max Act: 0.4434. Min Act: -0.0000

Data Index: 1632653 (The Pile)

Max Activating Token Index: 552

Text #9

Max Range: 0.5795. Min Range: -0.5795

Max Act: 0.3839. Min Act: -0.0000

Data Index: 1494573 (The Pile)

Max Activating Token Index: 762

Text #10

Max Range: 0.5795. Min Range: -0.5795

Max Act: 0.3967. Min Act: -0.0000

Data Index: 613167 (The Pile)

Max Activating Token Index: 402

Text #11

Max Range: 0.5795. Min Range: -0.5795

Max Act: 0.4362. Min Act: -0.0000

Data Index: 483116 (The Pile)

Max Activating Token Index: 626

Text #12

Max Range: 0.5795. Min Range: -0.5795

Max Act: 0.4066. Min Act: -0.0000

Data Index: 1606962 (The Pile)

Max Activating Token Index: 270

Text #13

Max Range: 0.5795. Min Range: -0.5795

Max Act: 0.4465. Min Act: -0.0000

Data Index: 832172 (The Pile)

Max Activating Token Index: 676

Text #14

Max Range: 0.5795. Min Range: -0.5795

Max Act: 0.3871. Min Act: -0.0000

Data Index: 1181141 (The Pile)

Max Activating Token Index: 870

Text #15

Max Range: 0.5795. Min Range: -0.5795

Max Act: 0.3703. Min Act: -0.0000

Data Index: 1893152 (The Pile)

Max Activating Token Index: 224

Text #16

Max Range: 0.5795. Min Range: -0.5795

Max Act: 0.2881. Min Act: -0.0000

Data Index: 51899 (The Pile)

Max Activating Token Index: 254

Text #17

Max Range: 0.5795. Min Range: -0.5795

Max Act: 0.4403. Min Act: -0.0000

Data Index: 348064 (The Pile)

Max Activating Token Index: 617

Text #18

Max Range: 0.5795. Min Range: -0.5795

Max Act: 0.4057. Min Act: -0.0000

Data Index: 796769 (The Pile)

Max Activating Token Index: 593

Text #19

Max Range: 0.5795. Min Range: -0.5795

Max Act: 0.4180. Min Act: -0.0000

Data Index: 1104311 (The Pile)

Max Activating Token Index: 605