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

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

Neuron 2259 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4610. Min Range: -5.4610

Max Act: 5.4610. Min Act: -0.0000

Data Index: 288501 (C4 (Web Text))

Max Activating Token Index: 879

Text #1

Max Range: 5.4610. Min Range: -5.4610

Max Act: 5.2943. Min Act: -0.0000

Data Index: 828891 (C4 (Web Text))

Max Activating Token Index: 704

Text #2

Max Range: 5.4610. Min Range: -5.4610

Max Act: 4.5258. Min Act: -0.0000

Data Index: 172580 (C4 (Web Text))

Max Activating Token Index: 495

Text #3

Max Range: 5.4610. Min Range: -5.4610

Max Act: 4.4620. Min Act: -0.0000

Data Index: 1062378 (C4 (Web Text))

Max Activating Token Index: 807

Text #4

Max Range: 5.4610. Min Range: -5.4610

Max Act: 4.3939. Min Act: -0.0000

Data Index: 64723 (C4 (Web Text))

Max Activating Token Index: 469

Text #5

Max Range: 5.4610. Min Range: -5.4610

Max Act: 3.9261. Min Act: -0.0000

Data Index: 659254 (C4 (Web Text))

Max Activating Token Index: 607

Text #6

Max Range: 5.4610. Min Range: -5.4610

Max Act: 3.8982. Min Act: -0.0000

Data Index: 1046786 (C4 (Web Text))

Max Activating Token Index: 947

Text #7

Max Range: 5.4610. Min Range: -5.4610

Max Act: 4.0413. Min Act: -0.0000

Data Index: 400367 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 5.4610. Min Range: -5.4610

Max Act: 3.8634. Min Act: -0.0000

Data Index: 1000714 (C4 (Web Text))

Max Activating Token Index: 132

Text #9

Max Range: 5.4610. Min Range: -5.4610

Max Act: 3.6837. Min Act: -0.0000

Data Index: 1347864 (C4 (Web Text))

Max Activating Token Index: 166

Text #10

Max Range: 5.4610. Min Range: -5.4610

Max Act: 4.1090. Min Act: -0.0000

Data Index: 496981 (C4 (Web Text))

Max Activating Token Index: 695

Text #11

Max Range: 5.4610. Min Range: -5.4610

Max Act: 3.7580. Min Act: -0.0000

Data Index: 661754 (C4 (Web Text))

Max Activating Token Index: 400

Text #12

Max Range: 5.4610. Min Range: -5.4610

Max Act: 3.5663. Min Act: -0.0000

Data Index: 572091 (C4 (Web Text))

Max Activating Token Index: 632

Text #13

Max Range: 5.4610. Min Range: -5.4610

Max Act: 3.9012. Min Act: -0.0000

Data Index: 1301526 (C4 (Web Text))

Max Activating Token Index: 647

Text #14

Max Range: 5.4610. Min Range: -5.4610

Max Act: 3.8582. Min Act: -0.0000

Data Index: 447180 (C4 (Web Text))

Max Activating Token Index: 413

Text #15

Max Range: 5.4610. Min Range: -5.4610

Max Act: 3.6556. Min Act: -0.0000

Data Index: 1245176 (C4 (Web Text))

Max Activating Token Index: 699

Text #16

Max Range: 5.4610. Min Range: -5.4610

Max Act: 3.6441. Min Act: -0.0000

Data Index: 1354724 (C4 (Web Text))

Max Activating Token Index: 935

Text #17

Max Range: 5.4610. Min Range: -5.4610

Max Act: 3.4240. Min Act: -0.0000

Data Index: 350093 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 5.4610. Min Range: -5.4610

Max Act: 3.7307. Min Act: -0.0000

Data Index: 1079685 (C4 (Web Text))

Max Activating Token Index: 74

Text #19

Max Range: 5.4610. Min Range: -5.4610

Max Act: 3.5628. Min Act: -0.0000

Data Index: 898357 (C4 (Web Text))

Max Activating Token Index: 949