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

Dataset: The Pile

Neuron 1153 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: 1.3807. Min Range: -1.3807

Max Act: 1.3807. Min Act: -0.0000

Data Index: 1735273 (The Pile)

Max Activating Token Index: 1003

Text #1

Max Range: 1.3807. Min Range: -1.3807

Max Act: 1.2428. Min Act: -0.0000

Data Index: 1517271 (The Pile)

Max Activating Token Index: 985

Text #2

Max Range: 1.3807. Min Range: -1.3807

Max Act: 1.1770. Min Act: -0.0000

Data Index: 995385 (The Pile)

Max Activating Token Index: 42

Text #3

Max Range: 1.3807. Min Range: -1.3807

Max Act: 1.0688. Min Act: -0.0000

Data Index: 1825273 (The Pile)

Max Activating Token Index: 687

Text #4

Max Range: 1.3807. Min Range: -1.3807

Max Act: 1.0337. Min Act: -0.0000

Data Index: 905220 (The Pile)

Max Activating Token Index: 989

Text #5

Max Range: 1.3807. Min Range: -1.3807

Max Act: 1.1286. Min Act: -0.0000

Data Index: 1528307 (The Pile)

Max Activating Token Index: 385

Text #6

Max Range: 1.3807. Min Range: -1.3807

Max Act: 0.9589. Min Act: -0.0000

Data Index: 1746426 (The Pile)

Max Activating Token Index: 513

Text #7

Max Range: 1.3807. Min Range: -1.3807

Max Act: 1.0710. Min Act: -0.0000

Data Index: 1242726 (The Pile)

Max Activating Token Index: 522

Text #8

Max Range: 1.3807. Min Range: -1.3807

Max Act: 0.9154. Min Act: -0.0000

Data Index: 181195 (The Pile)

Max Activating Token Index: 251

Text #9

Max Range: 1.3807. Min Range: -1.3807

Max Act: 0.8904. Min Act: -0.0000

Data Index: 1511029 (The Pile)

Max Activating Token Index: 357

Text #10

Max Range: 1.3807. Min Range: -1.3807

Max Act: 0.9154. Min Act: -0.0000

Data Index: 1602170 (The Pile)

Max Activating Token Index: 610

Text #11

Max Range: 1.3807. Min Range: -1.3807

Max Act: 0.9223. Min Act: -0.0000

Data Index: 1047840 (The Pile)

Max Activating Token Index: 860

Text #12

Max Range: 1.3807. Min Range: -1.3807

Max Act: 0.9251. Min Act: -0.0000

Data Index: 1608270 (The Pile)

Max Activating Token Index: 622

Text #13

Max Range: 1.3807. Min Range: -1.3807

Max Act: 0.9971. Min Act: -0.0000

Data Index: 293125 (The Pile)

Max Activating Token Index: 367

Text #14

Max Range: 1.3807. Min Range: -1.3807

Max Act: 0.8837. Min Act: -0.0000

Data Index: 1832261 (The Pile)

Max Activating Token Index: 51

Text #15

Max Range: 1.3807. Min Range: -1.3807

Max Act: 0.8705. Min Act: -0.0000

Data Index: 982779 (The Pile)

Max Activating Token Index: 767

Text #16

Max Range: 1.3807. Min Range: -1.3807

Max Act: 0.8170. Min Act: -0.0000

Data Index: 720683 (The Pile)

Max Activating Token Index: 726

Text #17

Max Range: 1.3807. Min Range: -1.3807

Max Act: 0.8759. Min Act: -0.0000

Data Index: 1171871 (The Pile)

Max Activating Token Index: 40

Text #18

Max Range: 1.3807. Min Range: -1.3807

Max Act: 0.8438. Min Act: -0.0000

Data Index: 1999167 (The Pile)

Max Activating Token Index: 203

Text #19

Max Range: 1.3807. Min Range: -1.3807

Max Act: 0.8242. Min Act: -0.0000

Data Index: 1985033 (The Pile)

Max Activating Token Index: 28