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

Dataset: The Pile

Neuron 3513 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5267. Min Range: -0.5267

Max Act: 0.5267. Min Act: -0.0000

Data Index: 1131942 (The Pile)

Max Activating Token Index: 642

Text #1

Max Range: 0.5267. Min Range: -0.5267

Max Act: 0.4016. Min Act: -0.0000

Data Index: 1283644 (The Pile)

Max Activating Token Index: 960

Text #2

Max Range: 0.5267. Min Range: -0.5267

Max Act: 0.3119. Min Act: -0.0000

Data Index: 1768661 (The Pile)

Max Activating Token Index: 767

Text #3

Max Range: 0.5267. Min Range: -0.5267

Max Act: 0.3047. Min Act: -0.0000

Data Index: 1037650 (The Pile)

Max Activating Token Index: 704

Text #4

Max Range: 0.5267. Min Range: -0.5267

Max Act: 0.2768. Min Act: -0.0000

Data Index: 1781954 (The Pile)

Max Activating Token Index: 83

Text #5

Max Range: 0.5267. Min Range: -0.5267

Max Act: 0.2870. Min Act: -0.0000

Data Index: 62984 (The Pile)

Max Activating Token Index: 792

Text #6

Max Range: 0.5267. Min Range: -0.5267

Max Act: 0.2919. Min Act: -0.0000

Data Index: 830182 (The Pile)

Max Activating Token Index: 551

Text #7

Max Range: 0.5267. Min Range: -0.5267

Max Act: 0.2816. Min Act: -0.0000

Data Index: 1201303 (The Pile)

Max Activating Token Index: 633

Text #8

Max Range: 0.5267. Min Range: -0.5267

Max Act: 0.3188. Min Act: -0.0000

Data Index: 1297286 (The Pile)

Max Activating Token Index: 182

Text #9

Max Range: 0.5267. Min Range: -0.5267

Max Act: 0.2118. Min Act: -0.0000

Data Index: 1493125 (The Pile)

Max Activating Token Index: 673

Text #10

Max Range: 0.5267. Min Range: -0.5267

Max Act: 0.2726. Min Act: -0.0000

Data Index: 1514901 (The Pile)

Max Activating Token Index: 533

Text #11

Max Range: 0.5267. Min Range: -0.5267

Max Act: 0.2596. Min Act: -0.0000

Data Index: 972830 (The Pile)

Max Activating Token Index: 436

Text #12

Max Range: 0.5267. Min Range: -0.5267

Max Act: 0.2570. Min Act: -0.0000

Data Index: 723319 (The Pile)

Max Activating Token Index: 461

Text #13

Max Range: 0.5267. Min Range: -0.5267

Max Act: 0.2579. Min Act: -0.0000

Data Index: 683172 (The Pile)

Max Activating Token Index: 811

Text #14

Max Range: 0.5267. Min Range: -0.5267

Max Act: 0.2338. Min Act: -0.0000

Data Index: 1994451 (The Pile)

Max Activating Token Index: 365

Text #15

Max Range: 0.5267. Min Range: -0.5267

Max Act: 0.2417. Min Act: -0.0000

Data Index: 354648 (The Pile)

Max Activating Token Index: 685

Text #16

Max Range: 0.5267. Min Range: -0.5267

Max Act: 0.2291. Min Act: -0.0000

Data Index: 1007356 (The Pile)

Max Activating Token Index: 21

Text #17

Max Range: 0.5267. Min Range: -0.5267

Max Act: 0.2200. Min Act: -0.0000

Data Index: 1508997 (The Pile)

Max Activating Token Index: 608

Text #18

Max Range: 0.5267. Min Range: -0.5267

Max Act: 0.2652. Min Act: -0.0000

Data Index: 1995731 (The Pile)

Max Activating Token Index: 160

Text #19

Max Range: 0.5267. Min Range: -0.5267

Max Act: 0.2421. Min Act: -0.0000

Data Index: 892093 (The Pile)

Max Activating Token Index: 116