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

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

Neuron 3450 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5804. Min Range: -1.5804

Max Act: 1.5015. Min Act: -0.0000

Data Index: 193561 (C4 (Web Text))

Max Activating Token Index: 404

Text #1

Max Range: 1.5804. Min Range: -1.5804

Max Act: 1.5804. Min Act: -0.0000

Data Index: 666075 (C4 (Web Text))

Max Activating Token Index: 972

Text #2

Max Range: 1.5804. Min Range: -1.5804

Max Act: 1.5208. Min Act: -0.0000

Data Index: 70838 (C4 (Web Text))

Max Activating Token Index: 810

Text #3

Max Range: 1.5804. Min Range: -1.5804

Max Act: 1.5307. Min Act: -0.0000

Data Index: 1280435 (C4 (Web Text))

Max Activating Token Index: 677

Text #4

Max Range: 1.5804. Min Range: -1.5804

Max Act: 1.5199. Min Act: -0.0000

Data Index: 57817 (C4 (Web Text))

Max Activating Token Index: 370

Text #5

Max Range: 1.5804. Min Range: -1.5804

Max Act: 1.4793. Min Act: -0.0000

Data Index: 1081497 (C4 (Web Text))

Max Activating Token Index: 835

Text #6

Max Range: 1.5804. Min Range: -1.5804

Max Act: 1.4261. Min Act: -0.0000

Data Index: 314133 (C4 (Web Text))

Max Activating Token Index: 135

Text #7

Max Range: 1.5804. Min Range: -1.5804

Max Act: 1.4832. Min Act: -0.0000

Data Index: 264462 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 1.5804. Min Range: -1.5804

Max Act: 1.4422. Min Act: -0.0000

Data Index: 54883 (C4 (Web Text))

Max Activating Token Index: 652

Text #9

Max Range: 1.5804. Min Range: -1.5804

Max Act: 1.3583. Min Act: -0.0000

Data Index: 98312 (C4 (Web Text))

Max Activating Token Index: 742

Text #10

Max Range: 1.5804. Min Range: -1.5804

Max Act: 1.4429. Min Act: -0.0000

Data Index: 384486 (C4 (Web Text))

Max Activating Token Index: 219

Text #11

Max Range: 1.5804. Min Range: -1.5804

Max Act: 1.4362. Min Act: -0.0000

Data Index: 644239 (C4 (Web Text))

Max Activating Token Index: 168

Text #12

Max Range: 1.5804. Min Range: -1.5804

Max Act: 1.3036. Min Act: -0.0000

Data Index: 994124 (C4 (Web Text))

Max Activating Token Index: 961

Text #13

Max Range: 1.5804. Min Range: -1.5804

Max Act: 1.4237. Min Act: -0.0000

Data Index: 554891 (C4 (Web Text))

Max Activating Token Index: 934

Text #14

Max Range: 1.5804. Min Range: -1.5804

Max Act: 1.4027. Min Act: -0.0000

Data Index: 1151491 (C4 (Web Text))

Max Activating Token Index: 60

Text #15

Max Range: 1.5804. Min Range: -1.5804

Max Act: 1.4408. Min Act: -0.0000

Data Index: 1228241 (C4 (Web Text))

Max Activating Token Index: 428

Text #16

Max Range: 1.5804. Min Range: -1.5804

Max Act: 1.3495. Min Act: -0.0000

Data Index: 509498 (C4 (Web Text))

Max Activating Token Index: 878

Text #17

Max Range: 1.5804. Min Range: -1.5804

Max Act: 1.3350. Min Act: -0.0000

Data Index: 651093 (C4 (Web Text))

Max Activating Token Index: 865

Text #18

Max Range: 1.5804. Min Range: -1.5804

Max Act: 1.3597. Min Act: -0.0000

Data Index: 822665 (C4 (Web Text))

Max Activating Token Index: 295

Text #19

Max Range: 1.5804. Min Range: -1.5804

Max Act: 1.3976. Min Act: -0.0000

Data Index: 495172 (C4 (Web Text))

Max Activating Token Index: 394