Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 78 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.8045. Min Act: -0.0000

Data Index: 885525 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.7324. Min Act: -0.0000

Data Index: 277375 (C4 (Web Text))

Max Activating Token Index: 340

Text #2

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.7067. Min Act: -0.0000

Data Index: 683429 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.6226. Min Act: -0.0000

Data Index: 713324 (C4 (Web Text))

Max Activating Token Index: 66

Text #4

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.5732. Min Act: -0.0000

Data Index: 1258592 (C4 (Web Text))

Max Activating Token Index: 938

Text #5

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.5658. Min Act: -0.0000

Data Index: 1318201 (C4 (Web Text))

Max Activating Token Index: 372

Text #6

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.5633. Min Act: -0.0000

Data Index: 264452 (C4 (Web Text))

Max Activating Token Index: 662

Text #7

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.5775. Min Act: -0.0000

Data Index: 293041 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.5779. Min Act: -0.0000

Data Index: 662574 (C4 (Web Text))

Max Activating Token Index: 37

Text #9

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.5718. Min Act: -0.0000

Data Index: 736021 (C4 (Web Text))

Max Activating Token Index: 110

Text #10

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.5123. Min Act: -0.0000

Data Index: 1090619 (C4 (Web Text))

Max Activating Token Index: 272

Text #11

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.5662. Min Act: -0.0000

Data Index: 1002656 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.5600. Min Act: -0.0000

Data Index: 523886 (C4 (Web Text))

Max Activating Token Index: 874

Text #13

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.5377. Min Act: -0.0000

Data Index: 579380 (C4 (Web Text))

Max Activating Token Index: 654

Text #14

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.5364. Min Act: -0.0000

Data Index: 984894 (C4 (Web Text))

Max Activating Token Index: 495

Text #15

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.5525. Min Act: -0.0000

Data Index: 1234744 (C4 (Web Text))

Max Activating Token Index: 699

Text #16

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.5299. Min Act: -0.0000

Data Index: 149123 (C4 (Web Text))

Max Activating Token Index: 101

Text #17

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.5497. Min Act: -0.0000

Data Index: 872720 (C4 (Web Text))

Max Activating Token Index: 278

Text #18

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.5332. Min Act: -0.0000

Data Index: 1140918 (C4 (Web Text))

Max Activating Token Index: 100

Text #19

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.5211. Min Act: -0.0000

Data Index: 120811 (C4 (Web Text))

Max Activating Token Index: 204