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

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

Neuron 2724 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: 3.3892. Min Range: -3.3892

Max Act: 3.3335. Min Act: -0.0000

Data Index: 119678 (C4 (Web Text))

Max Activating Token Index: 144

Text #1

Max Range: 3.3892. Min Range: -3.3892

Max Act: 3.3892. Min Act: -0.0000

Data Index: 573532 (C4 (Web Text))

Max Activating Token Index: 820

Text #2

Max Range: 3.3892. Min Range: -3.3892

Max Act: 3.3722. Min Act: -0.0000

Data Index: 47606 (C4 (Web Text))

Max Activating Token Index: 955

Text #3

Max Range: 3.3892. Min Range: -3.3892

Max Act: 3.0953. Min Act: -0.0000

Data Index: 715746 (C4 (Web Text))

Max Activating Token Index: 288

Text #4

Max Range: 3.3892. Min Range: -3.3892

Max Act: 2.5969. Min Act: -0.0000

Data Index: 733343 (C4 (Web Text))

Max Activating Token Index: 191

Text #5

Max Range: 3.3892. Min Range: -3.3892

Max Act: 2.4539. Min Act: -0.0000

Data Index: 260191 (C4 (Web Text))

Max Activating Token Index: 576

Text #6

Max Range: 3.3892. Min Range: -3.3892

Max Act: 2.2687. Min Act: -0.0000

Data Index: 669677 (C4 (Web Text))

Max Activating Token Index: 168

Text #7

Max Range: 3.3892. Min Range: -3.3892

Max Act: 2.1971. Min Act: -0.0000

Data Index: 868035 (C4 (Web Text))

Max Activating Token Index: 618

Text #8

Max Range: 3.3892. Min Range: -3.3892

Max Act: 2.2994. Min Act: -0.0000

Data Index: 1353829 (C4 (Web Text))

Max Activating Token Index: 15

Text #9

Max Range: 3.3892. Min Range: -3.3892

Max Act: 2.0398. Min Act: -0.0000

Data Index: 1347960 (C4 (Web Text))

Max Activating Token Index: 709

Text #10

Max Range: 3.3892. Min Range: -3.3892

Max Act: 2.0968. Min Act: -0.0000

Data Index: 638450 (C4 (Web Text))

Max Activating Token Index: 313

Text #11

Max Range: 3.3892. Min Range: -3.3892

Max Act: 2.0914. Min Act: -0.0000

Data Index: 1257440 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 3.3892. Min Range: -3.3892

Max Act: 2.1767. Min Act: -0.0000

Data Index: 1016943 (C4 (Web Text))

Max Activating Token Index: 711

Text #13

Max Range: 3.3892. Min Range: -3.3892

Max Act: 2.0617. Min Act: -0.0000

Data Index: 1337956 (C4 (Web Text))

Max Activating Token Index: 849

Text #14

Max Range: 3.3892. Min Range: -3.3892

Max Act: 2.0553. Min Act: -0.0000

Data Index: 242003 (C4 (Web Text))

Max Activating Token Index: 378

Text #15

Max Range: 3.3892. Min Range: -3.3892

Max Act: 2.1864. Min Act: -0.0000

Data Index: 706537 (C4 (Web Text))

Max Activating Token Index: 196

Text #16

Max Range: 3.3892. Min Range: -3.3892

Max Act: 1.9279. Min Act: -0.0000

Data Index: 1320308 (C4 (Web Text))

Max Activating Token Index: 636

Text #17

Max Range: 3.3892. Min Range: -3.3892

Max Act: 2.0159. Min Act: -0.0000

Data Index: 1159743 (C4 (Web Text))

Max Activating Token Index: 114

Text #18

Max Range: 3.3892. Min Range: -3.3892

Max Act: 1.9999. Min Act: -0.0000

Data Index: 772105 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 3.3892. Min Range: -3.3892

Max Act: 1.8750. Min Act: -0.0000

Data Index: 1176284 (C4 (Web Text))

Max Activating Token Index: 687