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

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

Neuron 2085 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.5640. Min Act: -0.0000

Data Index: 1337030 (C4 (Web Text))

Max Activating Token Index: 738

Text #1

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.5158. Min Act: -0.0000

Data Index: 486177 (C4 (Web Text))

Max Activating Token Index: 950

Text #2

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.5730. Min Act: -0.0000

Data Index: 417800 (C4 (Web Text))

Max Activating Token Index: 911

Text #3

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.5195. Min Act: -0.0000

Data Index: 328203 (C4 (Web Text))

Max Activating Token Index: 656

Text #4

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.5364. Min Act: -0.0000

Data Index: 738440 (C4 (Web Text))

Max Activating Token Index: 909

Text #5

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.5205. Min Act: -0.0000

Data Index: 35907 (C4 (Web Text))

Max Activating Token Index: 533

Text #6

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.5075. Min Act: -0.0000

Data Index: 962010 (C4 (Web Text))

Max Activating Token Index: 186

Text #7

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.5221. Min Act: -0.0000

Data Index: 88119 (C4 (Web Text))

Max Activating Token Index: 82

Text #8

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.4812. Min Act: -0.0000

Data Index: 1258963 (C4 (Web Text))

Max Activating Token Index: 717

Text #9

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.4664. Min Act: -0.0000

Data Index: 1031625 (C4 (Web Text))

Max Activating Token Index: 858

Text #10

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.4791. Min Act: -0.0000

Data Index: 1303098 (C4 (Web Text))

Max Activating Token Index: 441

Text #11

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.4427. Min Act: -0.0000

Data Index: 1256499 (C4 (Web Text))

Max Activating Token Index: 683

Text #12

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.4687. Min Act: -0.0000

Data Index: 240416 (C4 (Web Text))

Max Activating Token Index: 522

Text #13

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.4552. Min Act: -0.0000

Data Index: 529717 (C4 (Web Text))

Max Activating Token Index: 73

Text #14

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.4242. Min Act: -0.0000

Data Index: 1214266 (C4 (Web Text))

Max Activating Token Index: 775

Text #15

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.4448. Min Act: -0.0000

Data Index: 1202098 (C4 (Web Text))

Max Activating Token Index: 168

Text #16

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.4438. Min Act: -0.0000

Data Index: 177891 (C4 (Web Text))

Max Activating Token Index: 529

Text #17

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.4794. Min Act: -0.0000

Data Index: 51236 (C4 (Web Text))

Max Activating Token Index: 391

Text #18

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.4446. Min Act: -0.0000

Data Index: 319840 (C4 (Web Text))

Max Activating Token Index: 244

Text #19

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.4522. Min Act: -0.0000

Data Index: 249992 (C4 (Web Text))

Max Activating Token Index: 639