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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3752 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5646. Min Range: -0.5646

Max Act: 0.5646. Min Act: -0.0000

Data Index: 678610 (C4 (Web Text))

Max Activating Token Index: 411

Text #1

Max Range: 0.5646. Min Range: -0.5646

Max Act: 0.5077. Min Act: -0.0000

Data Index: 646030 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 0.5646. Min Range: -0.5646

Max Act: 0.4988. Min Act: -0.0000

Data Index: 1037019 (C4 (Web Text))

Max Activating Token Index: 655

Text #3

Max Range: 0.5646. Min Range: -0.5646

Max Act: 0.5224. Min Act: -0.0000

Data Index: 636726 (C4 (Web Text))

Max Activating Token Index: 781

Text #4

Max Range: 0.5646. Min Range: -0.5646

Max Act: 0.4843. Min Act: -0.0000

Data Index: 399213 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 0.5646. Min Range: -0.5646

Max Act: 0.5085. Min Act: -0.0000

Data Index: 459712 (C4 (Web Text))

Max Activating Token Index: 1021

Text #6

Max Range: 0.5646. Min Range: -0.5646

Max Act: 0.4525. Min Act: -0.0000

Data Index: 657687 (C4 (Web Text))

Max Activating Token Index: 493

Text #7

Max Range: 0.5646. Min Range: -0.5646

Max Act: 0.4549. Min Act: -0.0000

Data Index: 24397 (C4 (Web Text))

Max Activating Token Index: 903

Text #8

Max Range: 0.5646. Min Range: -0.5646

Max Act: 0.4358. Min Act: -0.0000

Data Index: 573144 (C4 (Web Text))

Max Activating Token Index: 83

Text #9

Max Range: 0.5646. Min Range: -0.5646

Max Act: 0.4689. Min Act: -0.0000

Data Index: 1048347 (C4 (Web Text))

Max Activating Token Index: 741

Text #10

Max Range: 0.5646. Min Range: -0.5646

Max Act: 0.4325. Min Act: -0.0000

Data Index: 945410 (C4 (Web Text))

Max Activating Token Index: 744

Text #11

Max Range: 0.5646. Min Range: -0.5646

Max Act: 0.4385. Min Act: -0.0000

Data Index: 49744 (C4 (Web Text))

Max Activating Token Index: 1022

Text #12

Max Range: 0.5646. Min Range: -0.5646

Max Act: 0.4175. Min Act: -0.0000

Data Index: 479291 (C4 (Web Text))

Max Activating Token Index: 1002

Text #13

Max Range: 0.5646. Min Range: -0.5646

Max Act: 0.4098. Min Act: -0.0000

Data Index: 827980 (C4 (Web Text))

Max Activating Token Index: 536

Text #14

Max Range: 0.5646. Min Range: -0.5646

Max Act: 0.4000. Min Act: -0.0000

Data Index: 1305398 (C4 (Web Text))

Max Activating Token Index: 54

Text #15

Max Range: 0.5646. Min Range: -0.5646

Max Act: 0.4658. Min Act: -0.0000

Data Index: 24826 (C4 (Web Text))

Max Activating Token Index: 178

Text #16

Max Range: 0.5646. Min Range: -0.5646

Max Act: 0.4082. Min Act: -0.0000

Data Index: 1187861 (C4 (Web Text))

Max Activating Token Index: 686

Text #17

Max Range: 0.5646. Min Range: -0.5646

Max Act: 0.4175. Min Act: -0.0000

Data Index: 1146484 (C4 (Web Text))

Max Activating Token Index: 415

Text #18

Max Range: 0.5646. Min Range: -0.5646

Max Act: 0.4012. Min Act: -0.0000

Data Index: 570906 (C4 (Web Text))

Max Activating Token Index: 311

Text #19

Max Range: 0.5646. Min Range: -0.5646

Max Act: 0.4199. Min Act: -0.0000

Data Index: 955106 (C4 (Web Text))

Max Activating Token Index: 1003