Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2780 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5903. Min Range: -0.5903

Max Act: 0.5716. Min Act: -0.0001

Data Index: 789143 (C4 (Web Text))

Max Activating Token Index: 878

Text #1

Max Range: 0.5903. Min Range: -0.5903

Max Act: 0.5903. Min Act: -0.0001

Data Index: 256145 (C4 (Web Text))

Max Activating Token Index: 92

Text #2

Max Range: 0.5903. Min Range: -0.5903

Max Act: 0.5630. Min Act: -0.0001

Data Index: 394901 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 0.5903. Min Range: -0.5903

Max Act: 0.5345. Min Act: -0.0001

Data Index: 257330 (C4 (Web Text))

Max Activating Token Index: 364

Text #4

Max Range: 0.5903. Min Range: -0.5903

Max Act: 0.5470. Min Act: -0.0001

Data Index: 550673 (C4 (Web Text))

Max Activating Token Index: 46

Text #5

Max Range: 0.5903. Min Range: -0.5903

Max Act: 0.5268. Min Act: -0.0001

Data Index: 493430 (C4 (Web Text))

Max Activating Token Index: 645

Text #6

Max Range: 0.5903. Min Range: -0.5903

Max Act: 0.5093. Min Act: -0.0001

Data Index: 174042 (C4 (Web Text))

Max Activating Token Index: 482

Text #7

Max Range: 0.5903. Min Range: -0.5903

Max Act: 0.5080. Min Act: -0.0001

Data Index: 836722 (C4 (Web Text))

Max Activating Token Index: 102

Text #8

Max Range: 0.5903. Min Range: -0.5903

Max Act: 0.5273. Min Act: -0.0001

Data Index: 150740 (C4 (Web Text))

Max Activating Token Index: 314

Text #9

Max Range: 0.5903. Min Range: -0.5903

Max Act: 0.5042. Min Act: -0.0001

Data Index: 1268873 (C4 (Web Text))

Max Activating Token Index: 255

Text #10

Max Range: 0.5903. Min Range: -0.5903

Max Act: 0.4697. Min Act: -0.0001

Data Index: 395670 (C4 (Web Text))

Max Activating Token Index: 872

Text #11

Max Range: 0.5903. Min Range: -0.5903

Max Act: 0.5164. Min Act: -0.0001

Data Index: 195248 (C4 (Web Text))

Max Activating Token Index: 975

Text #12

Max Range: 0.5903. Min Range: -0.5903

Max Act: 0.5008. Min Act: -0.0001

Data Index: 642212 (C4 (Web Text))

Max Activating Token Index: 562

Text #13

Max Range: 0.5903. Min Range: -0.5903

Max Act: 0.4812. Min Act: -0.0000

Data Index: 786585 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 0.5903. Min Range: -0.5903

Max Act: 0.4958. Min Act: -0.0001

Data Index: 828108 (C4 (Web Text))

Max Activating Token Index: 74

Text #15

Max Range: 0.5903. Min Range: -0.5903

Max Act: 0.5167. Min Act: -0.0000

Data Index: 1269148 (C4 (Web Text))

Max Activating Token Index: 896

Text #16

Max Range: 0.5903. Min Range: -0.5903

Max Act: 0.4751. Min Act: -0.0001

Data Index: 774434 (C4 (Web Text))

Max Activating Token Index: 92

Text #17

Max Range: 0.5903. Min Range: -0.5903

Max Act: 0.4829. Min Act: -0.0001

Data Index: 200977 (C4 (Web Text))

Max Activating Token Index: 151

Text #18

Max Range: 0.5903. Min Range: -0.5903

Max Act: 0.4862. Min Act: -0.0001

Data Index: 109729 (C4 (Web Text))

Max Activating Token Index: 350

Text #19

Max Range: 0.5903. Min Range: -0.5903

Max Act: 0.4660. Min Act: -0.0001

Data Index: 96247 (C4 (Web Text))

Max Activating Token Index: 687