Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1597 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.8900. Min Range: -0.8900

Max Act: 0.8614. Min Act: -0.0004

Data Index: 1175922 (C4 (Web Text))

Max Activating Token Index: 783

Text #1

Max Range: 0.8900. Min Range: -0.8900

Max Act: 0.8785. Min Act: -0.0004

Data Index: 99566 (C4 (Web Text))

Max Activating Token Index: 257

Text #2

Max Range: 0.8900. Min Range: -0.8900

Max Act: 0.8289. Min Act: -0.0004

Data Index: 1049726 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 0.8900. Min Range: -0.8900

Max Act: 0.8900. Min Act: -0.0004

Data Index: 413202 (C4 (Web Text))

Max Activating Token Index: 501

Text #4

Max Range: 0.8900. Min Range: -0.8900

Max Act: 0.8584. Min Act: -0.0004

Data Index: 764610 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 0.8900. Min Range: -0.8900

Max Act: 0.8539. Min Act: -0.0004

Data Index: 30617 (C4 (Web Text))

Max Activating Token Index: 616

Text #6

Max Range: 0.8900. Min Range: -0.8900

Max Act: 0.8784. Min Act: -0.0004

Data Index: 488791 (C4 (Web Text))

Max Activating Token Index: 571

Text #7

Max Range: 0.8900. Min Range: -0.8900

Max Act: 0.8167. Min Act: -0.0004

Data Index: 1221536 (C4 (Web Text))

Max Activating Token Index: 651

Text #8

Max Range: 0.8900. Min Range: -0.8900

Max Act: 0.8362. Min Act: -0.0004

Data Index: 990692 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 0.8900. Min Range: -0.8900

Max Act: 0.7806. Min Act: -0.0004

Data Index: 31603 (C4 (Web Text))

Max Activating Token Index: 753

Text #10

Max Range: 0.8900. Min Range: -0.8900

Max Act: 0.8286. Min Act: -0.0004

Data Index: 239518 (C4 (Web Text))

Max Activating Token Index: 1001

Text #11

Max Range: 0.8900. Min Range: -0.8900

Max Act: 0.8079. Min Act: -0.0004

Data Index: 189084 (C4 (Web Text))

Max Activating Token Index: 133

Text #12

Max Range: 0.8900. Min Range: -0.8900

Max Act: 0.7823. Min Act: -0.0004

Data Index: 97019 (C4 (Web Text))

Max Activating Token Index: 121

Text #13

Max Range: 0.8900. Min Range: -0.8900

Max Act: 0.8098. Min Act: -0.0004

Data Index: 1203073 (C4 (Web Text))

Max Activating Token Index: 422

Text #14

Max Range: 0.8900. Min Range: -0.8900

Max Act: 0.7790. Min Act: -0.0004

Data Index: 455279 (C4 (Web Text))

Max Activating Token Index: 278

Text #15

Max Range: 0.8900. Min Range: -0.8900

Max Act: 0.7314. Min Act: -0.0004

Data Index: 912739 (C4 (Web Text))

Max Activating Token Index: 825

Text #16

Max Range: 0.8900. Min Range: -0.8900

Max Act: 0.7698. Min Act: -0.0004

Data Index: 571036 (C4 (Web Text))

Max Activating Token Index: 822

Text #17

Max Range: 0.8900. Min Range: -0.8900

Max Act: 0.8195. Min Act: -0.0004

Data Index: 608108 (C4 (Web Text))

Max Activating Token Index: 524

Text #18

Max Range: 0.8900. Min Range: -0.8900

Max Act: 0.7911. Min Act: -0.0004

Data Index: 270627 (C4 (Web Text))

Max Activating Token Index: 993

Text #19

Max Range: 0.8900. Min Range: -0.8900

Max Act: 0.7676. Min Act: -0.0004

Data Index: 190837 (C4 (Web Text))

Max Activating Token Index: 389