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

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

Neuron 2049 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.5769. Min Act: -0.0001

Data Index: 740627 (C4 (Web Text))

Max Activating Token Index: 887

Text #1

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4792. Min Act: -0.0001

Data Index: 633636 (C4 (Web Text))

Max Activating Token Index: 221

Text #2

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4911. Min Act: -0.0001

Data Index: 52807 (C4 (Web Text))

Max Activating Token Index: 69

Text #3

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4826. Min Act: -0.0001

Data Index: 1151743 (C4 (Web Text))

Max Activating Token Index: 902

Text #4

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4683. Min Act: -0.0001

Data Index: 54443 (C4 (Web Text))

Max Activating Token Index: 480

Text #5

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4512. Min Act: -0.0001

Data Index: 79797 (C4 (Web Text))

Max Activating Token Index: 921

Text #6

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4512. Min Act: -0.0001

Data Index: 661807 (C4 (Web Text))

Max Activating Token Index: 9

Text #7

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4490. Min Act: -0.0002

Data Index: 875289 (C4 (Web Text))

Max Activating Token Index: 983

Text #8

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4342. Min Act: -0.0001

Data Index: 1001024 (C4 (Web Text))

Max Activating Token Index: 789

Text #9

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4784. Min Act: -0.0001

Data Index: 219003 (C4 (Web Text))

Max Activating Token Index: 729

Text #10

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4605. Min Act: -0.0001

Data Index: 519443 (C4 (Web Text))

Max Activating Token Index: 712

Text #11

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4374. Min Act: -0.0001

Data Index: 333392 (C4 (Web Text))

Max Activating Token Index: 564

Text #12

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4289. Min Act: -0.0001

Data Index: 200169 (C4 (Web Text))

Max Activating Token Index: 217

Text #13

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4210. Min Act: -0.0001

Data Index: 219448 (C4 (Web Text))

Max Activating Token Index: 734

Text #14

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4737. Min Act: -0.0001

Data Index: 4377 (C4 (Web Text))

Max Activating Token Index: 216

Text #15

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4251. Min Act: -0.0001

Data Index: 692483 (C4 (Web Text))

Max Activating Token Index: 443

Text #16

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.3914. Min Act: -0.0001

Data Index: 432447 (C4 (Web Text))

Max Activating Token Index: 589

Text #17

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4280. Min Act: -0.0001

Data Index: 576208 (C4 (Web Text))

Max Activating Token Index: 245

Text #18

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4066. Min Act: -0.0001

Data Index: 1279513 (C4 (Web Text))

Max Activating Token Index: 614

Text #19

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.3944. Min Act: -0.0002

Data Index: 433615 (C4 (Web Text))

Max Activating Token Index: 870