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

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

Neuron 2574 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: 0.7650. Min Range: -0.7650

Max Act: 0.7650. Min Act: -0.0001

Data Index: 959023 (C4 (Web Text))

Max Activating Token Index: 206

Text #1

Max Range: 0.7650. Min Range: -0.7650

Max Act: 0.5852. Min Act: -0.0000

Data Index: 1273509 (C4 (Web Text))

Max Activating Token Index: 195

Text #2

Max Range: 0.7650. Min Range: -0.7650

Max Act: 0.5220. Min Act: -0.0000

Data Index: 1287787 (C4 (Web Text))

Max Activating Token Index: 648

Text #3

Max Range: 0.7650. Min Range: -0.7650

Max Act: 0.4461. Min Act: -0.0000

Data Index: 161975 (C4 (Web Text))

Max Activating Token Index: 773

Text #4

Max Range: 0.7650. Min Range: -0.7650

Max Act: 0.5336. Min Act: -0.0000

Data Index: 248800 (C4 (Web Text))

Max Activating Token Index: 364

Text #5

Max Range: 0.7650. Min Range: -0.7650

Max Act: 0.5147. Min Act: -0.0000

Data Index: 914982 (C4 (Web Text))

Max Activating Token Index: 528

Text #6

Max Range: 0.7650. Min Range: -0.7650

Max Act: 0.4747. Min Act: -0.0000

Data Index: 896000 (C4 (Web Text))

Max Activating Token Index: 228

Text #7

Max Range: 0.7650. Min Range: -0.7650

Max Act: 0.5041. Min Act: -0.0000

Data Index: 491500 (C4 (Web Text))

Max Activating Token Index: 373

Text #8

Max Range: 0.7650. Min Range: -0.7650

Max Act: 0.4784. Min Act: -0.0000

Data Index: 70382 (C4 (Web Text))

Max Activating Token Index: 684

Text #9

Max Range: 0.7650. Min Range: -0.7650

Max Act: 0.4891. Min Act: -0.0000

Data Index: 130699 (C4 (Web Text))

Max Activating Token Index: 51

Text #10

Max Range: 0.7650. Min Range: -0.7650

Max Act: 0.4994. Min Act: -0.0000

Data Index: 640765 (C4 (Web Text))

Max Activating Token Index: 870

Text #11

Max Range: 0.7650. Min Range: -0.7650

Max Act: 0.5443. Min Act: -0.0000

Data Index: 155367 (C4 (Web Text))

Max Activating Token Index: 681

Text #12

Max Range: 0.7650. Min Range: -0.7650

Max Act: 0.4965. Min Act: -0.0000

Data Index: 320666 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 0.7650. Min Range: -0.7650

Max Act: 0.4739. Min Act: -0.0000

Data Index: 684579 (C4 (Web Text))

Max Activating Token Index: 930

Text #14

Max Range: 0.7650. Min Range: -0.7650

Max Act: 0.5078. Min Act: -0.0000

Data Index: 161547 (C4 (Web Text))

Max Activating Token Index: 277

Text #15

Max Range: 0.7650. Min Range: -0.7650

Max Act: 0.4696. Min Act: -0.0000

Data Index: 858838 (C4 (Web Text))

Max Activating Token Index: 189

Text #16

Max Range: 0.7650. Min Range: -0.7650

Max Act: 0.4706. Min Act: -0.0000

Data Index: 61930 (C4 (Web Text))

Max Activating Token Index: 405

Text #17

Max Range: 0.7650. Min Range: -0.7650

Max Act: 0.4664. Min Act: -0.0000

Data Index: 786932 (C4 (Web Text))

Max Activating Token Index: 733

Text #18

Max Range: 0.7650. Min Range: -0.7650

Max Act: 0.4590. Min Act: -0.0000

Data Index: 240959 (C4 (Web Text))

Max Activating Token Index: 804

Text #19

Max Range: 0.7650. Min Range: -0.7650

Max Act: 0.4133. Min Act: -0.0000

Data Index: 24825 (C4 (Web Text))

Max Activating Token Index: 265