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

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

Neuron 131 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0274. Min Range: -4.0274

Max Act: 4.0274. Min Act: -0.0001

Data Index: 545970 (C4 (Web Text))

Max Activating Token Index: 711

Text #1

Max Range: 4.0274. Min Range: -4.0274

Max Act: 3.7080. Min Act: -0.0001

Data Index: 467217 (C4 (Web Text))

Max Activating Token Index: 145

Text #2

Max Range: 4.0274. Min Range: -4.0274

Max Act: 3.4797. Min Act: -0.0001

Data Index: 966136 (C4 (Web Text))

Max Activating Token Index: 681

Text #3

Max Range: 4.0274. Min Range: -4.0274

Max Act: 4.0174. Min Act: -0.0001

Data Index: 1248665 (C4 (Web Text))

Max Activating Token Index: 784

Text #4

Max Range: 4.0274. Min Range: -4.0274

Max Act: 3.6384. Min Act: -0.0001

Data Index: 160571 (C4 (Web Text))

Max Activating Token Index: 943

Text #5

Max Range: 4.0274. Min Range: -4.0274

Max Act: 3.8887. Min Act: -0.0001

Data Index: 228915 (C4 (Web Text))

Max Activating Token Index: 112

Text #6

Max Range: 4.0274. Min Range: -4.0274

Max Act: 3.6908. Min Act: -0.0001

Data Index: 992167 (C4 (Web Text))

Max Activating Token Index: 77

Text #7

Max Range: 4.0274. Min Range: -4.0274

Max Act: 3.5488. Min Act: -0.0001

Data Index: 406366 (C4 (Web Text))

Max Activating Token Index: 109

Text #8

Max Range: 4.0274. Min Range: -4.0274

Max Act: 3.8315. Min Act: -0.0001

Data Index: 973058 (C4 (Web Text))

Max Activating Token Index: 155

Text #9

Max Range: 4.0274. Min Range: -4.0274

Max Act: 3.6459. Min Act: -0.0001

Data Index: 600639 (C4 (Web Text))

Max Activating Token Index: 816

Text #10

Max Range: 4.0274. Min Range: -4.0274

Max Act: 3.6285. Min Act: -0.0001

Data Index: 706651 (C4 (Web Text))

Max Activating Token Index: 851

Text #11

Max Range: 4.0274. Min Range: -4.0274

Max Act: 3.9305. Min Act: -0.0001

Data Index: 518006 (C4 (Web Text))

Max Activating Token Index: 326

Text #12

Max Range: 4.0274. Min Range: -4.0274

Max Act: 3.4285. Min Act: -0.0001

Data Index: 1204136 (C4 (Web Text))

Max Activating Token Index: 799

Text #13

Max Range: 4.0274. Min Range: -4.0274

Max Act: 3.3933. Min Act: -0.0001

Data Index: 32075 (C4 (Web Text))

Max Activating Token Index: 518

Text #14

Max Range: 4.0274. Min Range: -4.0274

Max Act: 3.5011. Min Act: -0.0001

Data Index: 39085 (C4 (Web Text))

Max Activating Token Index: 77

Text #15

Max Range: 4.0274. Min Range: -4.0274

Max Act: 3.7559. Min Act: -0.0001

Data Index: 998151 (C4 (Web Text))

Max Activating Token Index: 701

Text #16

Max Range: 4.0274. Min Range: -4.0274

Max Act: 3.5945. Min Act: -0.0001

Data Index: 190521 (C4 (Web Text))

Max Activating Token Index: 45

Text #17

Max Range: 4.0274. Min Range: -4.0274

Max Act: 3.5547. Min Act: -0.0001

Data Index: 4038 (C4 (Web Text))

Max Activating Token Index: 997

Text #18

Max Range: 4.0274. Min Range: -4.0274

Max Act: 3.2691. Min Act: -0.0001

Data Index: 703051 (C4 (Web Text))

Max Activating Token Index: 138

Text #19

Max Range: 4.0274. Min Range: -4.0274

Max Act: 3.4182. Min Act: -0.0001

Data Index: 965994 (C4 (Web Text))

Max Activating Token Index: 672