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

Dataset: The Pile

Neuron 2200 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: 0.8506. Min Range: -0.8506

Max Act: 0.8401. Min Act: -0.0000

Data Index: 1977980 (The Pile)

Max Activating Token Index: 269

Text #1

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.7675. Min Act: -0.0000

Data Index: 921344 (The Pile)

Max Activating Token Index: 908

Text #2

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.8506. Min Act: -0.0000

Data Index: 51790 (The Pile)

Max Activating Token Index: 904

Text #3

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.7993. Min Act: -0.0000

Data Index: 942413 (The Pile)

Max Activating Token Index: 219

Text #4

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.7723. Min Act: -0.0000

Data Index: 1704965 (The Pile)

Max Activating Token Index: 237

Text #5

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.7922. Min Act: -0.0000

Data Index: 1171011 (The Pile)

Max Activating Token Index: 288

Text #6

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.7644. Min Act: -0.0000

Data Index: 820582 (The Pile)

Max Activating Token Index: 246

Text #7

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.8053. Min Act: -0.0000

Data Index: 1165827 (The Pile)

Max Activating Token Index: 207

Text #8

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.7633. Min Act: -0.0000

Data Index: 342732 (The Pile)

Max Activating Token Index: 26

Text #9

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.7349. Min Act: -0.0000

Data Index: 1149516 (The Pile)

Max Activating Token Index: 307

Text #10

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.7182. Min Act: -0.0000

Data Index: 1817972 (The Pile)

Max Activating Token Index: 955

Text #11

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.7134. Min Act: -0.0000

Data Index: 53481 (The Pile)

Max Activating Token Index: 495

Text #12

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.7154. Min Act: -0.0000

Data Index: 865957 (The Pile)

Max Activating Token Index: 425

Text #13

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.6883. Min Act: -0.0000

Data Index: 43745 (The Pile)

Max Activating Token Index: 627

Text #14

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.6905. Min Act: -0.0000

Data Index: 1675910 (The Pile)

Max Activating Token Index: 417

Text #15

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.6338. Min Act: -0.0000

Data Index: 1978345 (The Pile)

Max Activating Token Index: 461

Text #16

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.7047. Min Act: -0.0000

Data Index: 384708 (The Pile)

Max Activating Token Index: 132

Text #17

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.6621. Min Act: -0.0000

Data Index: 1563684 (The Pile)

Max Activating Token Index: 197

Text #18

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.7048. Min Act: -0.0000

Data Index: 461490 (The Pile)

Max Activating Token Index: 299

Text #19

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.6826. Min Act: -0.0000

Data Index: 1289950 (The Pile)

Max Activating Token Index: 971