Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5866 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0838. Min Range: -1.0838

Max Act: 1.0838. Min Act: -0.0001

Data Index: 438991 (C4 (Web Text))

Max Activating Token Index: 806

Text #1

Max Range: 1.0838. Min Range: -1.0838

Max Act: 0.9637. Min Act: -0.0001

Data Index: 1337631 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 1.0838. Min Range: -1.0838

Max Act: 0.9374. Min Act: -0.0001

Data Index: 920766 (C4 (Web Text))

Max Activating Token Index: 981

Text #3

Max Range: 1.0838. Min Range: -1.0838

Max Act: 0.8721. Min Act: -0.0001

Data Index: 511202 (C4 (Web Text))

Max Activating Token Index: 642

Text #4

Max Range: 1.0838. Min Range: -1.0838

Max Act: 0.9451. Min Act: -0.0001

Data Index: 514119 (C4 (Web Text))

Max Activating Token Index: 639

Text #5

Max Range: 1.0838. Min Range: -1.0838

Max Act: 0.8813. Min Act: -0.0001

Data Index: 74178 (C4 (Web Text))

Max Activating Token Index: 505

Text #6

Max Range: 1.0838. Min Range: -1.0838

Max Act: 0.9259. Min Act: -0.0001

Data Index: 678726 (C4 (Web Text))

Max Activating Token Index: 278

Text #7

Max Range: 1.0838. Min Range: -1.0838

Max Act: 0.9497. Min Act: -0.0001

Data Index: 801273 (C4 (Web Text))

Max Activating Token Index: 1012

Text #8

Max Range: 1.0838. Min Range: -1.0838

Max Act: 0.9221. Min Act: -0.0001

Data Index: 203155 (C4 (Web Text))

Max Activating Token Index: 845

Text #9

Max Range: 1.0838. Min Range: -1.0838

Max Act: 0.8811. Min Act: -0.0001

Data Index: 824104 (C4 (Web Text))

Max Activating Token Index: 810

Text #10

Max Range: 1.0838. Min Range: -1.0838

Max Act: 0.7752. Min Act: -0.0001

Data Index: 546904 (C4 (Web Text))

Max Activating Token Index: 759

Text #11

Max Range: 1.0838. Min Range: -1.0838

Max Act: 0.8326. Min Act: -0.0001

Data Index: 664599 (C4 (Web Text))

Max Activating Token Index: 571

Text #12

Max Range: 1.0838. Min Range: -1.0838

Max Act: 0.9716. Min Act: -0.0001

Data Index: 1327017 (C4 (Web Text))

Max Activating Token Index: 323

Text #13

Max Range: 1.0838. Min Range: -1.0838

Max Act: 0.8218. Min Act: -0.0001

Data Index: 19940 (C4 (Web Text))

Max Activating Token Index: 964

Text #14

Max Range: 1.0838. Min Range: -1.0838

Max Act: 0.9003. Min Act: -0.0001

Data Index: 173019 (C4 (Web Text))

Max Activating Token Index: 164

Text #15

Max Range: 1.0838. Min Range: -1.0838

Max Act: 0.8491. Min Act: -0.0001

Data Index: 966390 (C4 (Web Text))

Max Activating Token Index: 501

Text #16

Max Range: 1.0838. Min Range: -1.0838

Max Act: 0.8185. Min Act: -0.0000

Data Index: 1444163 (Python Code)

Max Activating Token Index: 811

Text #17

Max Range: 1.0838. Min Range: -1.0838

Max Act: 0.7931. Min Act: -0.0000

Data Index: 1387732 (Python Code)

Max Activating Token Index: 326

Text #18

Max Range: 1.0838. Min Range: -1.0838

Max Act: 0.7915. Min Act: -0.0000

Data Index: 1606156 (Python Code)

Max Activating Token Index: 512

Text #19

Max Range: 1.0838. Min Range: -1.0838

Max Act: 0.7001. Min Act: -0.0001

Data Index: 1557091 (Python Code)

Max Activating Token Index: 314