Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 509 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.6926. Min Range: -1.6926

Max Act: 1.6926. Min Act: -0.0002

Data Index: 657941 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 1.6926. Min Range: -1.6926

Max Act: 1.6615. Min Act: -0.0002

Data Index: 187604 (C4 (Web Text))

Max Activating Token Index: 911

Text #2

Max Range: 1.6926. Min Range: -1.6926

Max Act: 1.6657. Min Act: -0.0002

Data Index: 1078462 (C4 (Web Text))

Max Activating Token Index: 863

Text #3

Max Range: 1.6926. Min Range: -1.6926

Max Act: 1.5780. Min Act: -0.0001

Data Index: 215897 (C4 (Web Text))

Max Activating Token Index: 833

Text #4

Max Range: 1.6926. Min Range: -1.6926

Max Act: 1.6224. Min Act: -0.0002

Data Index: 252836 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 1.6926. Min Range: -1.6926

Max Act: 1.6683. Min Act: -0.0002

Data Index: 2474 (C4 (Web Text))

Max Activating Token Index: 807

Text #6

Max Range: 1.6926. Min Range: -1.6926

Max Act: 1.6194. Min Act: -0.0002

Data Index: 856151 (C4 (Web Text))

Max Activating Token Index: 916

Text #7

Max Range: 1.6926. Min Range: -1.6926

Max Act: 1.5729. Min Act: -0.0002

Data Index: 737691 (C4 (Web Text))

Max Activating Token Index: 889

Text #8

Max Range: 1.6926. Min Range: -1.6926

Max Act: 1.5785. Min Act: -0.0002

Data Index: 162408 (C4 (Web Text))

Max Activating Token Index: 941

Text #9

Max Range: 1.6926. Min Range: -1.6926

Max Act: 1.5212. Min Act: -0.0002

Data Index: 447708 (C4 (Web Text))

Max Activating Token Index: 928

Text #10

Max Range: 1.6926. Min Range: -1.6926

Max Act: 1.5268. Min Act: -0.0002

Data Index: 217791 (C4 (Web Text))

Max Activating Token Index: 897

Text #11

Max Range: 1.6926. Min Range: -1.6926

Max Act: 1.4406. Min Act: -0.0002

Data Index: 1334717 (C4 (Web Text))

Max Activating Token Index: 978

Text #12

Max Range: 1.6926. Min Range: -1.6926

Max Act: 1.5188. Min Act: -0.0001

Data Index: 560657 (C4 (Web Text))

Max Activating Token Index: 978

Text #13

Max Range: 1.6926. Min Range: -1.6926

Max Act: 1.6456. Min Act: -0.0002

Data Index: 293368 (C4 (Web Text))

Max Activating Token Index: 948

Text #14

Max Range: 1.6926. Min Range: -1.6926

Max Act: 1.5150. Min Act: -0.0002

Data Index: 1105423 (C4 (Web Text))

Max Activating Token Index: 834

Text #15

Max Range: 1.6926. Min Range: -1.6926

Max Act: 1.5658. Min Act: -0.0002

Data Index: 940889 (C4 (Web Text))

Max Activating Token Index: 871

Text #16

Max Range: 1.6926. Min Range: -1.6926

Max Act: 1.5531. Min Act: -0.0002

Data Index: 1099352 (C4 (Web Text))

Max Activating Token Index: 1002

Text #17

Max Range: 1.6926. Min Range: -1.6926

Max Act: 1.4701. Min Act: -0.0002

Data Index: 41446 (C4 (Web Text))

Max Activating Token Index: 392

Text #18

Max Range: 1.6926. Min Range: -1.6926

Max Act: 1.5878. Min Act: -0.0002

Data Index: 1316356 (C4 (Web Text))

Max Activating Token Index: 738

Text #19

Max Range: 1.6926. Min Range: -1.6926

Max Act: 1.5121. Min Act: -0.0002

Data Index: 661693 (C4 (Web Text))

Max Activating Token Index: 679