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

Dataset: The Pile

Neuron 471 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: 0.8259. Min Range: -0.8259

Max Act: 0.8259. Min Act: -0.0000

Data Index: 565280 (The Pile)

Max Activating Token Index: 101

Text #1

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.6326. Min Act: -0.0000

Data Index: 1154377 (The Pile)

Max Activating Token Index: 179

Text #2

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.6026. Min Act: -0.0000

Data Index: 1026271 (The Pile)

Max Activating Token Index: 293

Text #3

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.5854. Min Act: -0.0000

Data Index: 157173 (The Pile)

Max Activating Token Index: 927

Text #4

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.5608. Min Act: -0.0000

Data Index: 657420 (The Pile)

Max Activating Token Index: 68

Text #5

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.5637. Min Act: -0.0000

Data Index: 375777 (The Pile)

Max Activating Token Index: 657

Text #6

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.5358. Min Act: -0.0000

Data Index: 894335 (The Pile)

Max Activating Token Index: 559

Text #7

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.4861. Min Act: -0.0000

Data Index: 1298880 (The Pile)

Max Activating Token Index: 189

Text #8

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.5296. Min Act: -0.0000

Data Index: 1778056 (The Pile)

Max Activating Token Index: 998

Text #9

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.4934. Min Act: -0.0000

Data Index: 1328196 (The Pile)

Max Activating Token Index: 540

Text #10

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.4734. Min Act: -0.0000

Data Index: 1594891 (The Pile)

Max Activating Token Index: 564

Text #11

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.4868. Min Act: -0.0000

Data Index: 1824490 (The Pile)

Max Activating Token Index: 434

Text #12

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.5040. Min Act: -0.0000

Data Index: 1071029 (The Pile)

Max Activating Token Index: 347

Text #13

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.5007. Min Act: -0.0000

Data Index: 1853706 (The Pile)

Max Activating Token Index: 506

Text #14

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.4752. Min Act: -0.0000

Data Index: 1713339 (The Pile)

Max Activating Token Index: 465

Text #15

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.4772. Min Act: -0.0000

Data Index: 1154467 (The Pile)

Max Activating Token Index: 342

Text #16

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.4710. Min Act: -0.0000

Data Index: 1015798 (The Pile)

Max Activating Token Index: 343

Text #17

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.4642. Min Act: -0.0000

Data Index: 101977 (The Pile)

Max Activating Token Index: 903

Text #18

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.4654. Min Act: -0.0000

Data Index: 653173 (The Pile)

Max Activating Token Index: 947

Text #19

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.4778. Min Act: -0.0000

Data Index: 794114 (The Pile)

Max Activating Token Index: 903