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

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

Neuron 734 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.7005. Min Range: -1.7005

Max Act: 1.7005. Min Act: -0.0000

Data Index: 811762 (C4 (Web Text))

Max Activating Token Index: 679

Text #1

Max Range: 1.7005. Min Range: -1.7005

Max Act: 1.5214. Min Act: -0.0000

Data Index: 1097146 (C4 (Web Text))

Max Activating Token Index: 717

Text #2

Max Range: 1.7005. Min Range: -1.7005

Max Act: 1.5000. Min Act: -0.0000

Data Index: 781322 (C4 (Web Text))

Max Activating Token Index: 848

Text #3

Max Range: 1.7005. Min Range: -1.7005

Max Act: 1.3468. Min Act: -0.0000

Data Index: 1094664 (C4 (Web Text))

Max Activating Token Index: 825

Text #4

Max Range: 1.7005. Min Range: -1.7005

Max Act: 1.3403. Min Act: -0.0000

Data Index: 879107 (C4 (Web Text))

Max Activating Token Index: 124

Text #5

Max Range: 1.7005. Min Range: -1.7005

Max Act: 1.3394. Min Act: -0.0000

Data Index: 936500 (C4 (Web Text))

Max Activating Token Index: 883

Text #6

Max Range: 1.7005. Min Range: -1.7005

Max Act: 1.3445. Min Act: -0.0000

Data Index: 272468 (C4 (Web Text))

Max Activating Token Index: 752

Text #7

Max Range: 1.7005. Min Range: -1.7005

Max Act: 1.3329. Min Act: -0.0000

Data Index: 147503 (C4 (Web Text))

Max Activating Token Index: 947

Text #8

Max Range: 1.7005. Min Range: -1.7005

Max Act: 1.4980. Min Act: -0.0000

Data Index: 672501 (C4 (Web Text))

Max Activating Token Index: 898

Text #9

Max Range: 1.7005. Min Range: -1.7005

Max Act: 1.3929. Min Act: -0.0000

Data Index: 183983 (C4 (Web Text))

Max Activating Token Index: 590

Text #10

Max Range: 1.7005. Min Range: -1.7005

Max Act: 1.3017. Min Act: -0.0000

Data Index: 131099 (C4 (Web Text))

Max Activating Token Index: 357

Text #11

Max Range: 1.7005. Min Range: -1.7005

Max Act: 1.3715. Min Act: -0.0000

Data Index: 298796 (C4 (Web Text))

Max Activating Token Index: 529

Text #12

Max Range: 1.7005. Min Range: -1.7005

Max Act: 1.3632. Min Act: -0.0000

Data Index: 597070 (C4 (Web Text))

Max Activating Token Index: 654

Text #13

Max Range: 1.7005. Min Range: -1.7005

Max Act: 1.3559. Min Act: -0.0000

Data Index: 660471 (C4 (Web Text))

Max Activating Token Index: 840

Text #14

Max Range: 1.7005. Min Range: -1.7005

Max Act: 1.2643. Min Act: -0.0000

Data Index: 782871 (C4 (Web Text))

Max Activating Token Index: 848

Text #15

Max Range: 1.7005. Min Range: -1.7005

Max Act: 1.1820. Min Act: -0.0000

Data Index: 227306 (C4 (Web Text))

Max Activating Token Index: 905

Text #16

Max Range: 1.7005. Min Range: -1.7005

Max Act: 1.2941. Min Act: -0.0000

Data Index: 5282 (C4 (Web Text))

Max Activating Token Index: 947

Text #17

Max Range: 1.7005. Min Range: -1.7005

Max Act: 1.3799. Min Act: -0.0000

Data Index: 535705 (C4 (Web Text))

Max Activating Token Index: 245

Text #18

Max Range: 1.7005. Min Range: -1.7005

Max Act: 1.3822. Min Act: -0.0000

Data Index: 290736 (C4 (Web Text))

Max Activating Token Index: 455

Text #19

Max Range: 1.7005. Min Range: -1.7005

Max Act: 1.2354. Min Act: -0.0000

Data Index: 432512 (C4 (Web Text))

Max Activating Token Index: 908