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

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

Neuron 2096 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6390. Min Range: -1.6390

Max Act: 1.6390. Min Act: -0.0001

Data Index: 1077901 (C4 (Web Text))

Max Activating Token Index: 983

Text #1

Max Range: 1.6390. Min Range: -1.6390

Max Act: 1.6108. Min Act: -0.0001

Data Index: 931007 (C4 (Web Text))

Max Activating Token Index: 470

Text #2

Max Range: 1.6390. Min Range: -1.6390

Max Act: 1.5069. Min Act: -0.0001

Data Index: 674585 (C4 (Web Text))

Max Activating Token Index: 66

Text #3

Max Range: 1.6390. Min Range: -1.6390

Max Act: 1.5392. Min Act: -0.0001

Data Index: 642935 (C4 (Web Text))

Max Activating Token Index: 296

Text #4

Max Range: 1.6390. Min Range: -1.6390

Max Act: 1.5346. Min Act: -0.0001

Data Index: 913023 (C4 (Web Text))

Max Activating Token Index: 554

Text #5

Max Range: 1.6390. Min Range: -1.6390

Max Act: 1.3552. Min Act: -0.0001

Data Index: 643976 (C4 (Web Text))

Max Activating Token Index: 278

Text #6

Max Range: 1.6390. Min Range: -1.6390

Max Act: 1.4945. Min Act: -0.0001

Data Index: 426856 (C4 (Web Text))

Max Activating Token Index: 623

Text #7

Max Range: 1.6390. Min Range: -1.6390

Max Act: 1.3847. Min Act: -0.0001

Data Index: 1225371 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 1.6390. Min Range: -1.6390

Max Act: 1.4619. Min Act: -0.0001

Data Index: 1292665 (C4 (Web Text))

Max Activating Token Index: 842

Text #9

Max Range: 1.6390. Min Range: -1.6390

Max Act: 1.4185. Min Act: -0.0001

Data Index: 812033 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 1.6390. Min Range: -1.6390

Max Act: 1.3512. Min Act: -0.0001

Data Index: 964962 (C4 (Web Text))

Max Activating Token Index: 682

Text #11

Max Range: 1.6390. Min Range: -1.6390

Max Act: 1.2599. Min Act: -0.0001

Data Index: 1351709 (C4 (Web Text))

Max Activating Token Index: 754

Text #12

Max Range: 1.6390. Min Range: -1.6390

Max Act: 1.3400. Min Act: -0.0001

Data Index: 766189 (C4 (Web Text))

Max Activating Token Index: 859

Text #13

Max Range: 1.6390. Min Range: -1.6390

Max Act: 1.2936. Min Act: -0.0001

Data Index: 336606 (C4 (Web Text))

Max Activating Token Index: 362

Text #14

Max Range: 1.6390. Min Range: -1.6390

Max Act: 1.3287. Min Act: -0.0001

Data Index: 655015 (C4 (Web Text))

Max Activating Token Index: 573

Text #15

Max Range: 1.6390. Min Range: -1.6390

Max Act: 1.2777. Min Act: -0.0000

Data Index: 666119 (C4 (Web Text))

Max Activating Token Index: 849

Text #16

Max Range: 1.6390. Min Range: -1.6390

Max Act: 1.2180. Min Act: -0.0001

Data Index: 322271 (C4 (Web Text))

Max Activating Token Index: 899

Text #17

Max Range: 1.6390. Min Range: -1.6390

Max Act: 1.3414. Min Act: -0.0001

Data Index: 854568 (C4 (Web Text))

Max Activating Token Index: 403

Text #18

Max Range: 1.6390. Min Range: -1.6390

Max Act: 1.2724. Min Act: -0.0000

Data Index: 348041 (C4 (Web Text))

Max Activating Token Index: 999

Text #19

Max Range: 1.6390. Min Range: -1.6390

Max Act: 1.2403. Min Act: -0.0001

Data Index: 693765 (C4 (Web Text))

Max Activating Token Index: 31