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

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

Neuron 4135 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.5127. Min Act: -0.0000

Data Index: 46069 (C4 (Web Text))

Max Activating Token Index: 922

Text #1

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.4871. Min Act: -0.0000

Data Index: 475808 (C4 (Web Text))

Max Activating Token Index: 154

Text #2

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.4672. Min Act: -0.0000

Data Index: 61346 (C4 (Web Text))

Max Activating Token Index: 868

Text #3

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.4010. Min Act: -0.0000

Data Index: 381298 (C4 (Web Text))

Max Activating Token Index: 504

Text #4

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.4107. Min Act: -0.0000

Data Index: 219497 (C4 (Web Text))

Max Activating Token Index: 63

Text #5

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.4091. Min Act: -0.0000

Data Index: 526774 (C4 (Web Text))

Max Activating Token Index: 657

Text #6

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.3966. Min Act: -0.0000

Data Index: 1230201 (C4 (Web Text))

Max Activating Token Index: 914

Text #7

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.3900. Min Act: -0.0000

Data Index: 986573 (C4 (Web Text))

Max Activating Token Index: 356

Text #8

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.4018. Min Act: -0.0000

Data Index: 576488 (C4 (Web Text))

Max Activating Token Index: 538

Text #9

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.4019. Min Act: -0.0000

Data Index: 1264869 (C4 (Web Text))

Max Activating Token Index: 891

Text #10

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.3738. Min Act: -0.0000

Data Index: 753899 (C4 (Web Text))

Max Activating Token Index: 237

Text #11

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.3873. Min Act: -0.0000

Data Index: 333442 (C4 (Web Text))

Max Activating Token Index: 721

Text #12

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.3660. Min Act: -0.0000

Data Index: 497004 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.3737. Min Act: -0.0000

Data Index: 676556 (C4 (Web Text))

Max Activating Token Index: 280

Text #14

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.3337. Min Act: -0.0000

Data Index: 547 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.3433. Min Act: -0.0000

Data Index: 1162358 (C4 (Web Text))

Max Activating Token Index: 495

Text #16

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.3455. Min Act: -0.0000

Data Index: 961531 (C4 (Web Text))

Max Activating Token Index: 804

Text #17

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.3293. Min Act: -0.0000

Data Index: 774711 (C4 (Web Text))

Max Activating Token Index: 792

Text #18

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.3560. Min Act: -0.0000

Data Index: 112725 (C4 (Web Text))

Max Activating Token Index: 227

Text #19

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.3383. Min Act: -0.0000

Data Index: 1150379 (C4 (Web Text))

Max Activating Token Index: 228