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

Dataset: The Pile

Neuron 4240 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2909. Min Range: -1.2909

Max Act: 1.2176. Min Act: -0.0000

Data Index: 1032648 (The Pile)

Max Activating Token Index: 875

Text #1

Max Range: 1.2909. Min Range: -1.2909

Max Act: 1.2909. Min Act: -0.0000

Data Index: 1467104 (The Pile)

Max Activating Token Index: 315

Text #2

Max Range: 1.2909. Min Range: -1.2909

Max Act: 0.9668. Min Act: -0.0000

Data Index: 1120687 (The Pile)

Max Activating Token Index: 683

Text #3

Max Range: 1.2909. Min Range: -1.2909

Max Act: 1.0656. Min Act: -0.0000

Data Index: 1130522 (The Pile)

Max Activating Token Index: 401

Text #4

Max Range: 1.2909. Min Range: -1.2909

Max Act: 1.2703. Min Act: -0.0000

Data Index: 1412921 (The Pile)

Max Activating Token Index: 238

Text #5

Max Range: 1.2909. Min Range: -1.2909

Max Act: 1.2361. Min Act: -0.0000

Data Index: 634439 (The Pile)

Max Activating Token Index: 616

Text #6

Max Range: 1.2909. Min Range: -1.2909

Max Act: 1.1664. Min Act: -0.0000

Data Index: 1586732 (The Pile)

Max Activating Token Index: 589

Text #7

Max Range: 1.2909. Min Range: -1.2909

Max Act: 1.0742. Min Act: -0.0000

Data Index: 1987544 (The Pile)

Max Activating Token Index: 295

Text #8

Max Range: 1.2909. Min Range: -1.2909

Max Act: 1.0091. Min Act: -0.0000

Data Index: 1970279 (The Pile)

Max Activating Token Index: 837

Text #9

Max Range: 1.2909. Min Range: -1.2909

Max Act: 0.9960. Min Act: -0.0000

Data Index: 1079116 (The Pile)

Max Activating Token Index: 412

Text #10

Max Range: 1.2909. Min Range: -1.2909

Max Act: 0.9723. Min Act: -0.0000

Data Index: 228501 (The Pile)

Max Activating Token Index: 176

Text #11

Max Range: 1.2909. Min Range: -1.2909

Max Act: 0.8871. Min Act: -0.0000

Data Index: 833158 (The Pile)

Max Activating Token Index: 631

Text #12

Max Range: 1.2909. Min Range: -1.2909

Max Act: 0.9810. Min Act: -0.0000

Data Index: 629097 (The Pile)

Max Activating Token Index: 810

Text #13

Max Range: 1.2909. Min Range: -1.2909

Max Act: 1.0421. Min Act: -0.0000

Data Index: 962091 (The Pile)

Max Activating Token Index: 254

Text #14

Max Range: 1.2909. Min Range: -1.2909

Max Act: 1.0146. Min Act: -0.0000

Data Index: 1546568 (The Pile)

Max Activating Token Index: 492

Text #15

Max Range: 1.2909. Min Range: -1.2909

Max Act: 0.9017. Min Act: -0.0000

Data Index: 904016 (The Pile)

Max Activating Token Index: 688

Text #16

Max Range: 1.2909. Min Range: -1.2909

Max Act: 1.2099. Min Act: -0.0000

Data Index: 130603 (The Pile)

Max Activating Token Index: 832

Text #17

Max Range: 1.2909. Min Range: -1.2909

Max Act: 0.7408. Min Act: -0.0000

Data Index: 472908 (The Pile)

Max Activating Token Index: 966

Text #18

Max Range: 1.2909. Min Range: -1.2909

Max Act: 1.0355. Min Act: -0.0000

Data Index: 352199 (The Pile)

Max Activating Token Index: 566

Text #19

Max Range: 1.2909. Min Range: -1.2909

Max Act: 0.8055. Min Act: -0.0000

Data Index: 751994 (The Pile)

Max Activating Token Index: 576