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

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

Neuron 141 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: 1.4683. Min Range: -1.4683

Max Act: 1.4683. Min Act: -0.0000

Data Index: 731573 (C4 (Web Text))

Max Activating Token Index: 517

Text #1

Max Range: 1.4683. Min Range: -1.4683

Max Act: 1.3646. Min Act: -0.0000

Data Index: 452854 (C4 (Web Text))

Max Activating Token Index: 958

Text #2

Max Range: 1.4683. Min Range: -1.4683

Max Act: 1.2030. Min Act: -0.0000

Data Index: 1054912 (C4 (Web Text))

Max Activating Token Index: 73

Text #3

Max Range: 1.4683. Min Range: -1.4683

Max Act: 1.2768. Min Act: -0.0000

Data Index: 711899 (C4 (Web Text))

Max Activating Token Index: 225

Text #4

Max Range: 1.4683. Min Range: -1.4683

Max Act: 1.2749. Min Act: -0.0000

Data Index: 109612 (C4 (Web Text))

Max Activating Token Index: 666

Text #5

Max Range: 1.4683. Min Range: -1.4683

Max Act: 1.1860. Min Act: -0.0001

Data Index: 1328791 (C4 (Web Text))

Max Activating Token Index: 362

Text #6

Max Range: 1.4683. Min Range: -1.4683

Max Act: 1.1679. Min Act: -0.0000

Data Index: 221452 (C4 (Web Text))

Max Activating Token Index: 120

Text #7

Max Range: 1.4683. Min Range: -1.4683

Max Act: 1.1591. Min Act: -0.0000

Data Index: 619884 (C4 (Web Text))

Max Activating Token Index: 822

Text #8

Max Range: 1.4683. Min Range: -1.4683

Max Act: 1.2526. Min Act: -0.0001

Data Index: 621712 (C4 (Web Text))

Max Activating Token Index: 719

Text #9

Max Range: 1.4683. Min Range: -1.4683

Max Act: 1.1543. Min Act: -0.0000

Data Index: 584513 (C4 (Web Text))

Max Activating Token Index: 8

Text #10

Max Range: 1.4683. Min Range: -1.4683

Max Act: 1.0719. Min Act: -0.0000

Data Index: 384698 (C4 (Web Text))

Max Activating Token Index: 794

Text #11

Max Range: 1.4683. Min Range: -1.4683

Max Act: 1.0665. Min Act: -0.0000

Data Index: 681310 (C4 (Web Text))

Max Activating Token Index: 853

Text #12

Max Range: 1.4683. Min Range: -1.4683

Max Act: 1.0585. Min Act: -0.0000

Data Index: 573077 (C4 (Web Text))

Max Activating Token Index: 486

Text #13

Max Range: 1.4683. Min Range: -1.4683

Max Act: 1.1283. Min Act: -0.0001

Data Index: 565014 (C4 (Web Text))

Max Activating Token Index: 770

Text #14

Max Range: 1.4683. Min Range: -1.4683

Max Act: 1.0044. Min Act: -0.0000

Data Index: 709728 (C4 (Web Text))

Max Activating Token Index: 325

Text #15

Max Range: 1.4683. Min Range: -1.4683

Max Act: 1.0535. Min Act: -0.0000

Data Index: 1324292 (C4 (Web Text))

Max Activating Token Index: 497

Text #16

Max Range: 1.4683. Min Range: -1.4683

Max Act: 0.9896. Min Act: -0.0001

Data Index: 331697 (C4 (Web Text))

Max Activating Token Index: 956

Text #17

Max Range: 1.4683. Min Range: -1.4683

Max Act: 0.9864. Min Act: -0.0000

Data Index: 1113152 (C4 (Web Text))

Max Activating Token Index: 299

Text #18

Max Range: 1.4683. Min Range: -1.4683

Max Act: 1.0875. Min Act: -0.0000

Data Index: 980132 (C4 (Web Text))

Max Activating Token Index: 749

Text #19

Max Range: 1.4683. Min Range: -1.4683

Max Act: 1.1563. Min Act: -0.0000

Data Index: 376098 (C4 (Web Text))

Max Activating Token Index: 249