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

Dataset: The Pile

Neuron 4954 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6776. Min Range: -0.6776

Max Act: 0.6685. Min Act: -0.0000

Data Index: 670658 (The Pile)

Max Activating Token Index: 289

Text #1

Max Range: 0.6776. Min Range: -0.6776

Max Act: 0.6776. Min Act: -0.0000

Data Index: 745719 (The Pile)

Max Activating Token Index: 723

Text #2

Max Range: 0.6776. Min Range: -0.6776

Max Act: 0.6536. Min Act: -0.0000

Data Index: 1820384 (The Pile)

Max Activating Token Index: 341

Text #3

Max Range: 0.6776. Min Range: -0.6776

Max Act: 0.6300. Min Act: -0.0000

Data Index: 629061 (The Pile)

Max Activating Token Index: 133

Text #4

Max Range: 0.6776. Min Range: -0.6776

Max Act: 0.6168. Min Act: -0.0000

Data Index: 515987 (The Pile)

Max Activating Token Index: 481

Text #5

Max Range: 0.6776. Min Range: -0.6776

Max Act: 0.6145. Min Act: -0.0000

Data Index: 1196812 (The Pile)

Max Activating Token Index: 873

Text #6

Max Range: 0.6776. Min Range: -0.6776

Max Act: 0.5736. Min Act: -0.0000

Data Index: 1864625 (The Pile)

Max Activating Token Index: 454

Text #7

Max Range: 0.6776. Min Range: -0.6776

Max Act: 0.5505. Min Act: -0.0000

Data Index: 359831 (The Pile)

Max Activating Token Index: 625

Text #8

Max Range: 0.6776. Min Range: -0.6776

Max Act: 0.5887. Min Act: -0.0000

Data Index: 68241 (The Pile)

Max Activating Token Index: 34

Text #9

Max Range: 0.6776. Min Range: -0.6776

Max Act: 0.5840. Min Act: -0.0000

Data Index: 1605673 (The Pile)

Max Activating Token Index: 182

Text #10

Max Range: 0.6776. Min Range: -0.6776

Max Act: 0.5901. Min Act: -0.0000

Data Index: 664270 (The Pile)

Max Activating Token Index: 770

Text #11

Max Range: 0.6776. Min Range: -0.6776

Max Act: 0.6174. Min Act: -0.0000

Data Index: 1491211 (The Pile)

Max Activating Token Index: 630

Text #12

Max Range: 0.6776. Min Range: -0.6776

Max Act: 0.5824. Min Act: -0.0000

Data Index: 112337 (The Pile)

Max Activating Token Index: 323

Text #13

Max Range: 0.6776. Min Range: -0.6776

Max Act: 0.5339. Min Act: -0.0000

Data Index: 819200 (The Pile)

Max Activating Token Index: 348

Text #14

Max Range: 0.6776. Min Range: -0.6776

Max Act: 0.5091. Min Act: -0.0000

Data Index: 1562712 (The Pile)

Max Activating Token Index: 801

Text #15

Max Range: 0.6776. Min Range: -0.6776

Max Act: 0.5119. Min Act: -0.0000

Data Index: 221877 (The Pile)

Max Activating Token Index: 252

Text #16

Max Range: 0.6776. Min Range: -0.6776

Max Act: 0.5143. Min Act: 0.0000

Data Index: 282933 (The Pile)

Max Activating Token Index: 895

Text #17

Max Range: 0.6776. Min Range: -0.6776

Max Act: 0.5130. Min Act: -0.0000

Data Index: 1933990 (The Pile)

Max Activating Token Index: 174

Text #18

Max Range: 0.6776. Min Range: -0.6776

Max Act: 0.5041. Min Act: -0.0000

Data Index: 1222266 (The Pile)

Max Activating Token Index: 713

Text #19

Max Range: 0.6776. Min Range: -0.6776

Max Act: 0.4822. Min Act: -0.0000

Data Index: 749879 (The Pile)

Max Activating Token Index: 36