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

Dataset: The Pile

Neuron 2645 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: 0.5594. Min Range: -0.5594

Max Act: 0.5594. Min Act: -0.0000

Data Index: 397803 (The Pile)

Max Activating Token Index: 506

Text #1

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.5449. Min Act: -0.0000

Data Index: 1194450 (The Pile)

Max Activating Token Index: 585

Text #2

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.5224. Min Act: -0.0000

Data Index: 1948562 (The Pile)

Max Activating Token Index: 322

Text #3

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4653. Min Act: -0.0000

Data Index: 917820 (The Pile)

Max Activating Token Index: 934

Text #4

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.5000. Min Act: -0.0000

Data Index: 1057450 (The Pile)

Max Activating Token Index: 606

Text #5

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4834. Min Act: -0.0000

Data Index: 127884 (The Pile)

Max Activating Token Index: 957

Text #6

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4773. Min Act: -0.0000

Data Index: 32044 (The Pile)

Max Activating Token Index: 908

Text #7

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4128. Min Act: -0.0000

Data Index: 489529 (The Pile)

Max Activating Token Index: 941

Text #8

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4529. Min Act: -0.0000

Data Index: 488465 (The Pile)

Max Activating Token Index: 781

Text #9

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4314. Min Act: -0.0000

Data Index: 205382 (The Pile)

Max Activating Token Index: 322

Text #10

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4246. Min Act: -0.0000

Data Index: 75498 (The Pile)

Max Activating Token Index: 443

Text #11

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4248. Min Act: -0.0000

Data Index: 1156115 (The Pile)

Max Activating Token Index: 929

Text #12

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.3986. Min Act: -0.0000

Data Index: 766182 (The Pile)

Max Activating Token Index: 954

Text #13

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4175. Min Act: -0.0000

Data Index: 375671 (The Pile)

Max Activating Token Index: 633

Text #14

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.3886. Min Act: -0.0000

Data Index: 114114 (The Pile)

Max Activating Token Index: 466

Text #15

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4406. Min Act: -0.0000

Data Index: 47390 (The Pile)

Max Activating Token Index: 304

Text #16

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4109. Min Act: -0.0000

Data Index: 852947 (The Pile)

Max Activating Token Index: 229

Text #17

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4251. Min Act: -0.0000

Data Index: 1445117 (The Pile)

Max Activating Token Index: 843

Text #18

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4141. Min Act: -0.0000

Data Index: 1957748 (The Pile)

Max Activating Token Index: 281

Text #19

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4252. Min Act: -0.0000

Data Index: 1119956 (The Pile)

Max Activating Token Index: 669