Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2970 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6252. Min Range: -0.6252

Max Act: 0.6252. Min Act: -0.0000

Data Index: 273365 (The Pile)

Max Activating Token Index: 208

Text #1

Max Range: 0.6252. Min Range: -0.6252

Max Act: 0.5853. Min Act: -0.0000

Data Index: 1426434 (The Pile)

Max Activating Token Index: 258

Text #2

Max Range: 0.6252. Min Range: -0.6252

Max Act: 0.5150. Min Act: -0.0000

Data Index: 353164 (The Pile)

Max Activating Token Index: 538

Text #3

Max Range: 0.6252. Min Range: -0.6252

Max Act: 0.5311. Min Act: -0.0000

Data Index: 1281394 (The Pile)

Max Activating Token Index: 673

Text #4

Max Range: 0.6252. Min Range: -0.6252

Max Act: 0.5039. Min Act: -0.0000

Data Index: 699521 (The Pile)

Max Activating Token Index: 328

Text #5

Max Range: 0.6252. Min Range: -0.6252

Max Act: 0.5157. Min Act: -0.0000

Data Index: 1649738 (The Pile)

Max Activating Token Index: 416

Text #6

Max Range: 0.6252. Min Range: -0.6252

Max Act: 0.5191. Min Act: -0.0000

Data Index: 1952817 (The Pile)

Max Activating Token Index: 602

Text #7

Max Range: 0.6252. Min Range: -0.6252

Max Act: 0.4812. Min Act: -0.0000

Data Index: 942472 (The Pile)

Max Activating Token Index: 471

Text #8

Max Range: 0.6252. Min Range: -0.6252

Max Act: 0.5107. Min Act: -0.0000

Data Index: 194855 (The Pile)

Max Activating Token Index: 740

Text #9

Max Range: 0.6252. Min Range: -0.6252

Max Act: 0.4741. Min Act: -0.0000

Data Index: 1279758 (The Pile)

Max Activating Token Index: 652

Text #10

Max Range: 0.6252. Min Range: -0.6252

Max Act: 0.4894. Min Act: -0.0000

Data Index: 1736687 (The Pile)

Max Activating Token Index: 812

Text #11

Max Range: 0.6252. Min Range: -0.6252

Max Act: 0.4576. Min Act: -0.0000

Data Index: 1974171 (The Pile)

Max Activating Token Index: 884

Text #12

Max Range: 0.6252. Min Range: -0.6252

Max Act: 0.4534. Min Act: -0.0000

Data Index: 732684 (The Pile)

Max Activating Token Index: 882

Text #13

Max Range: 0.6252. Min Range: -0.6252

Max Act: 0.4389. Min Act: -0.0000

Data Index: 1081415 (The Pile)

Max Activating Token Index: 988

Text #14

Max Range: 0.6252. Min Range: -0.6252

Max Act: 0.4819. Min Act: -0.0000

Data Index: 818444 (The Pile)

Max Activating Token Index: 284

Text #15

Max Range: 0.6252. Min Range: -0.6252

Max Act: 0.4245. Min Act: -0.0000

Data Index: 1037872 (The Pile)

Max Activating Token Index: 777

Text #16

Max Range: 0.6252. Min Range: -0.6252

Max Act: 0.4615. Min Act: 0.0000

Data Index: 380371 (The Pile)

Max Activating Token Index: 380

Text #17

Max Range: 0.6252. Min Range: -0.6252

Max Act: 0.4571. Min Act: -0.0000

Data Index: 703799 (The Pile)

Max Activating Token Index: 381

Text #18

Max Range: 0.6252. Min Range: -0.6252

Max Act: 0.4696. Min Act: -0.0000

Data Index: 182993 (The Pile)

Max Activating Token Index: 874

Text #19

Max Range: 0.6252. Min Range: -0.6252

Max Act: 0.4534. Min Act: 0.0000

Data Index: 1962717 (The Pile)

Max Activating Token Index: 271