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

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

Neuron 726 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4337. Min Range: -3.4337

Max Act: 3.4337. Min Act: -0.0000

Data Index: 731350 (C4 (Web Text))

Max Activating Token Index: 964

Text #1

Max Range: 3.4337. Min Range: -3.4337

Max Act: 3.3721. Min Act: -0.0000

Data Index: 1281485 (C4 (Web Text))

Max Activating Token Index: 823

Text #2

Max Range: 3.4337. Min Range: -3.4337

Max Act: 3.0848. Min Act: -0.0000

Data Index: 590727 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 3.4337. Min Range: -3.4337

Max Act: 3.0782. Min Act: -0.0000

Data Index: 363457 (C4 (Web Text))

Max Activating Token Index: 871

Text #4

Max Range: 3.4337. Min Range: -3.4337

Max Act: 3.0468. Min Act: -0.0000

Data Index: 920680 (C4 (Web Text))

Max Activating Token Index: 1018

Text #5

Max Range: 3.4337. Min Range: -3.4337

Max Act: 3.0410. Min Act: -0.0000

Data Index: 764639 (C4 (Web Text))

Max Activating Token Index: 981

Text #6

Max Range: 3.4337. Min Range: -3.4337

Max Act: 2.8849. Min Act: -0.0000

Data Index: 1131842 (C4 (Web Text))

Max Activating Token Index: 1005

Text #7

Max Range: 3.4337. Min Range: -3.4337

Max Act: 3.0310. Min Act: -0.0000

Data Index: 21605 (C4 (Web Text))

Max Activating Token Index: 189

Text #8

Max Range: 3.4337. Min Range: -3.4337

Max Act: 3.0298. Min Act: -0.0000

Data Index: 679227 (C4 (Web Text))

Max Activating Token Index: 687

Text #9

Max Range: 3.4337. Min Range: -3.4337

Max Act: 3.0242. Min Act: -0.0000

Data Index: 190073 (C4 (Web Text))

Max Activating Token Index: 845

Text #10

Max Range: 3.4337. Min Range: -3.4337

Max Act: 3.0062. Min Act: -0.0000

Data Index: 919331 (C4 (Web Text))

Max Activating Token Index: 547

Text #11

Max Range: 3.4337. Min Range: -3.4337

Max Act: 3.0087. Min Act: -0.0000

Data Index: 887608 (C4 (Web Text))

Max Activating Token Index: 581

Text #12

Max Range: 3.4337. Min Range: -3.4337

Max Act: 2.9692. Min Act: -0.0000

Data Index: 179335 (C4 (Web Text))

Max Activating Token Index: 667

Text #13

Max Range: 3.4337. Min Range: -3.4337

Max Act: 3.1406. Min Act: -0.0000

Data Index: 1132248 (C4 (Web Text))

Max Activating Token Index: 600

Text #14

Max Range: 3.4337. Min Range: -3.4337

Max Act: 2.9715. Min Act: -0.0000

Data Index: 805683 (C4 (Web Text))

Max Activating Token Index: 715

Text #15

Max Range: 3.4337. Min Range: -3.4337

Max Act: 3.0742. Min Act: -0.0000

Data Index: 127157 (C4 (Web Text))

Max Activating Token Index: 626

Text #16

Max Range: 3.4337. Min Range: -3.4337

Max Act: 2.9392. Min Act: -0.0000

Data Index: 591201 (C4 (Web Text))

Max Activating Token Index: 755

Text #17

Max Range: 3.4337. Min Range: -3.4337

Max Act: 2.9513. Min Act: -0.0000

Data Index: 899833 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 3.4337. Min Range: -3.4337

Max Act: 2.9579. Min Act: -0.0000

Data Index: 1354664 (C4 (Web Text))

Max Activating Token Index: 673

Text #19

Max Range: 3.4337. Min Range: -3.4337

Max Act: 2.9421. Min Act: -0.0000

Data Index: 796545 (C4 (Web Text))

Max Activating Token Index: 1005