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

Dataset: The Pile

Neuron 655 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: 1.9491. Min Range: -1.9491

Max Act: 1.9002. Min Act: -0.0000

Data Index: 1568901 (The Pile)

Max Activating Token Index: 862

Text #1

Max Range: 1.9491. Min Range: -1.9491

Max Act: 1.9491. Min Act: -0.0000

Data Index: 640196 (The Pile)

Max Activating Token Index: 755

Text #2

Max Range: 1.9491. Min Range: -1.9491

Max Act: 1.8796. Min Act: -0.0000

Data Index: 327487 (The Pile)

Max Activating Token Index: 752

Text #3

Max Range: 1.9491. Min Range: -1.9491

Max Act: 1.8528. Min Act: -0.0000

Data Index: 51231 (The Pile)

Max Activating Token Index: 732

Text #4

Max Range: 1.9491. Min Range: -1.9491

Max Act: 1.8378. Min Act: -0.0000

Data Index: 1265723 (The Pile)

Max Activating Token Index: 480

Text #5

Max Range: 1.9491. Min Range: -1.9491

Max Act: 1.7396. Min Act: -0.0000

Data Index: 165710 (The Pile)

Max Activating Token Index: 748

Text #6

Max Range: 1.9491. Min Range: -1.9491

Max Act: 1.8230. Min Act: -0.0000

Data Index: 1616626 (The Pile)

Max Activating Token Index: 215

Text #7

Max Range: 1.9491. Min Range: -1.9491

Max Act: 1.5693. Min Act: -0.0000

Data Index: 164441 (The Pile)

Max Activating Token Index: 461

Text #8

Max Range: 1.9491. Min Range: -1.9491

Max Act: 1.6340. Min Act: -0.0000

Data Index: 1418065 (The Pile)

Max Activating Token Index: 165

Text #9

Max Range: 1.9491. Min Range: -1.9491

Max Act: 1.5560. Min Act: -0.0000

Data Index: 1310575 (The Pile)

Max Activating Token Index: 808

Text #10

Max Range: 1.9491. Min Range: -1.9491

Max Act: 1.5920. Min Act: -0.0000

Data Index: 817329 (The Pile)

Max Activating Token Index: 275

Text #11

Max Range: 1.9491. Min Range: -1.9491

Max Act: 1.4884. Min Act: -0.0000

Data Index: 84383 (The Pile)

Max Activating Token Index: 943

Text #12

Max Range: 1.9491. Min Range: -1.9491

Max Act: 1.5387. Min Act: -0.0000

Data Index: 770976 (The Pile)

Max Activating Token Index: 958

Text #13

Max Range: 1.9491. Min Range: -1.9491

Max Act: 1.4488. Min Act: -0.0000

Data Index: 1835957 (The Pile)

Max Activating Token Index: 984

Text #14

Max Range: 1.9491. Min Range: -1.9491

Max Act: 1.5540. Min Act: -0.0000

Data Index: 818367 (The Pile)

Max Activating Token Index: 303

Text #15

Max Range: 1.9491. Min Range: -1.9491

Max Act: 1.5094. Min Act: -0.0000

Data Index: 795811 (The Pile)

Max Activating Token Index: 661

Text #16

Max Range: 1.9491. Min Range: -1.9491

Max Act: 1.4525. Min Act: -0.0000

Data Index: 833701 (The Pile)

Max Activating Token Index: 218

Text #17

Max Range: 1.9491. Min Range: -1.9491

Max Act: 1.4177. Min Act: -0.0000

Data Index: 408752 (The Pile)

Max Activating Token Index: 736

Text #18

Max Range: 1.9491. Min Range: -1.9491

Max Act: 1.4740. Min Act: -0.0000

Data Index: 190794 (The Pile)

Max Activating Token Index: 1022

Text #19

Max Range: 1.9491. Min Range: -1.9491

Max Act: 1.5765. Min Act: -0.0000

Data Index: 362775 (The Pile)

Max Activating Token Index: 589