Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2329 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 2.0675. Min Range: -2.0675

Max Act: 2.0675. Min Act: -0.0000

Data Index: 15325 (C4 (Web Text))

Max Activating Token Index: 880

Text #1

Max Range: 2.0675. Min Range: -2.0675

Max Act: 1.8315. Min Act: -0.0001

Data Index: 445503 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 2.0675. Min Range: -2.0675

Max Act: 1.4585. Min Act: -0.0001

Data Index: 873781 (C4 (Web Text))

Max Activating Token Index: 968

Text #3

Max Range: 2.0675. Min Range: -2.0675

Max Act: 1.5760. Min Act: -0.0001

Data Index: 70782 (C4 (Web Text))

Max Activating Token Index: 522

Text #4

Max Range: 2.0675. Min Range: -2.0675

Max Act: 1.4466. Min Act: -0.0000

Data Index: 354649 (C4 (Web Text))

Max Activating Token Index: 55

Text #5

Max Range: 2.0675. Min Range: -2.0675

Max Act: 1.4372. Min Act: -0.0001

Data Index: 277069 (C4 (Web Text))

Max Activating Token Index: 549

Text #6

Max Range: 2.0675. Min Range: -2.0675

Max Act: 1.2556. Min Act: -0.0000

Data Index: 1038070 (C4 (Web Text))

Max Activating Token Index: 134

Text #7

Max Range: 2.0675. Min Range: -2.0675

Max Act: 1.2411. Min Act: -0.0000

Data Index: 531227 (C4 (Web Text))

Max Activating Token Index: 781

Text #8

Max Range: 2.0675. Min Range: -2.0675

Max Act: 1.2751. Min Act: -0.0001

Data Index: 952990 (C4 (Web Text))

Max Activating Token Index: 998

Text #9

Max Range: 2.0675. Min Range: -2.0675

Max Act: 1.2653. Min Act: -0.0000

Data Index: 480181 (C4 (Web Text))

Max Activating Token Index: 610

Text #10

Max Range: 2.0675. Min Range: -2.0675

Max Act: 1.2337. Min Act: -0.0000

Data Index: 983506 (C4 (Web Text))

Max Activating Token Index: 327

Text #11

Max Range: 2.0675. Min Range: -2.0675

Max Act: 1.2144. Min Act: -0.0000

Data Index: 986633 (C4 (Web Text))

Max Activating Token Index: 140

Text #12

Max Range: 2.0675. Min Range: -2.0675

Max Act: 1.1551. Min Act: -0.0000

Data Index: 54150 (C4 (Web Text))

Max Activating Token Index: 577

Text #13

Max Range: 2.0675. Min Range: -2.0675

Max Act: 1.2603. Min Act: -0.0001

Data Index: 282398 (C4 (Web Text))

Max Activating Token Index: 722

Text #14

Max Range: 2.0675. Min Range: -2.0675

Max Act: 1.1825. Min Act: -0.0001

Data Index: 1163059 (C4 (Web Text))

Max Activating Token Index: 293

Text #15

Max Range: 2.0675. Min Range: -2.0675

Max Act: 1.1599. Min Act: -0.0001

Data Index: 903304 (C4 (Web Text))

Max Activating Token Index: 920

Text #16

Max Range: 2.0675. Min Range: -2.0675

Max Act: 1.1506. Min Act: -0.0000

Data Index: 956988 (C4 (Web Text))

Max Activating Token Index: 547

Text #17

Max Range: 2.0675. Min Range: -2.0675

Max Act: 1.1051. Min Act: -0.0001

Data Index: 433937 (C4 (Web Text))

Max Activating Token Index: 53

Text #18

Max Range: 2.0675. Min Range: -2.0675

Max Act: 1.0948. Min Act: -0.0000

Data Index: 956883 (C4 (Web Text))

Max Activating Token Index: 967

Text #19

Max Range: 2.0675. Min Range: -2.0675

Max Act: 1.1036. Min Act: -0.0000

Data Index: 1354753 (C4 (Web Text))

Max Activating Token Index: 351