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

Dataset: The Pile

Neuron 2288 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: 0.8762. Min Range: -0.8762

Max Act: 0.8762. Min Act: -0.0000

Data Index: 167328 (The Pile)

Max Activating Token Index: 991

Text #1

Max Range: 0.8762. Min Range: -0.8762

Max Act: 0.7800. Min Act: -0.0000

Data Index: 932314 (The Pile)

Max Activating Token Index: 306

Text #2

Max Range: 0.8762. Min Range: -0.8762

Max Act: 0.7068. Min Act: -0.0000

Data Index: 305214 (The Pile)

Max Activating Token Index: 941

Text #3

Max Range: 0.8762. Min Range: -0.8762

Max Act: 0.6806. Min Act: -0.0000

Data Index: 51191 (The Pile)

Max Activating Token Index: 960

Text #4

Max Range: 0.8762. Min Range: -0.8762

Max Act: 0.7477. Min Act: -0.0000

Data Index: 773705 (The Pile)

Max Activating Token Index: 834

Text #5

Max Range: 0.8762. Min Range: -0.8762

Max Act: 0.7796. Min Act: -0.0000

Data Index: 1884439 (The Pile)

Max Activating Token Index: 770

Text #6

Max Range: 0.8762. Min Range: -0.8762

Max Act: 0.7364. Min Act: -0.0000

Data Index: 1098457 (The Pile)

Max Activating Token Index: 84

Text #7

Max Range: 0.8762. Min Range: -0.8762

Max Act: 0.7125. Min Act: -0.0000

Data Index: 430272 (The Pile)

Max Activating Token Index: 654

Text #8

Max Range: 0.8762. Min Range: -0.8762

Max Act: 0.6779. Min Act: -0.0000

Data Index: 1124565 (The Pile)

Max Activating Token Index: 46

Text #9

Max Range: 0.8762. Min Range: -0.8762

Max Act: 0.6616. Min Act: -0.0000

Data Index: 1161583 (The Pile)

Max Activating Token Index: 343

Text #10

Max Range: 0.8762. Min Range: -0.8762

Max Act: 0.6823. Min Act: -0.0000

Data Index: 1293247 (The Pile)

Max Activating Token Index: 878

Text #11

Max Range: 0.8762. Min Range: -0.8762

Max Act: 0.6653. Min Act: -0.0000

Data Index: 1057885 (The Pile)

Max Activating Token Index: 393

Text #12

Max Range: 0.8762. Min Range: -0.8762

Max Act: 0.6808. Min Act: -0.0000

Data Index: 1359860 (The Pile)

Max Activating Token Index: 852

Text #13

Max Range: 0.8762. Min Range: -0.8762

Max Act: 0.6578. Min Act: -0.0000

Data Index: 1292600 (The Pile)

Max Activating Token Index: 355

Text #14

Max Range: 0.8762. Min Range: -0.8762

Max Act: 0.6039. Min Act: -0.0000

Data Index: 482236 (The Pile)

Max Activating Token Index: 392

Text #15

Max Range: 0.8762. Min Range: -0.8762

Max Act: 0.6153. Min Act: -0.0000

Data Index: 715663 (The Pile)

Max Activating Token Index: 342

Text #16

Max Range: 0.8762. Min Range: -0.8762

Max Act: 0.6160. Min Act: -0.0000

Data Index: 308278 (The Pile)

Max Activating Token Index: 193

Text #17

Max Range: 0.8762. Min Range: -0.8762

Max Act: 0.6292. Min Act: -0.0000

Data Index: 351052 (The Pile)

Max Activating Token Index: 485

Text #18

Max Range: 0.8762. Min Range: -0.8762

Max Act: 0.7067. Min Act: -0.0000

Data Index: 242551 (The Pile)

Max Activating Token Index: 878

Text #19

Max Range: 0.8762. Min Range: -0.8762

Max Act: 0.6638. Min Act: -0.0000

Data Index: 654386 (The Pile)

Max Activating Token Index: 1003