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

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

Neuron 4543 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8610. Min Range: -1.8610

Max Act: 1.8610. Min Act: -0.0000

Data Index: 1131424 (C4 (Web Text))

Max Activating Token Index: 228

Text #1

Max Range: 1.8610. Min Range: -1.8610

Max Act: 1.6967. Min Act: -0.0000

Data Index: 834862 (C4 (Web Text))

Max Activating Token Index: 534

Text #2

Max Range: 1.8610. Min Range: -1.8610

Max Act: 1.6495. Min Act: -0.0000

Data Index: 248385 (C4 (Web Text))

Max Activating Token Index: 885

Text #3

Max Range: 1.8610. Min Range: -1.8610

Max Act: 1.6400. Min Act: -0.0000

Data Index: 294307 (C4 (Web Text))

Max Activating Token Index: 530

Text #4

Max Range: 1.8610. Min Range: -1.8610

Max Act: 1.4669. Min Act: -0.0000

Data Index: 1247271 (C4 (Web Text))

Max Activating Token Index: 293

Text #5

Max Range: 1.8610. Min Range: -1.8610

Max Act: 1.3887. Min Act: -0.0000

Data Index: 710082 (C4 (Web Text))

Max Activating Token Index: 272

Text #6

Max Range: 1.8610. Min Range: -1.8610

Max Act: 1.4074. Min Act: -0.0000

Data Index: 502919 (C4 (Web Text))

Max Activating Token Index: 951

Text #7

Max Range: 1.8610. Min Range: -1.8610

Max Act: 1.2895. Min Act: -0.0000

Data Index: 1524800 (Python Code)

Max Activating Token Index: 31

Text #8

Max Range: 1.8610. Min Range: -1.8610

Max Act: 1.4079. Min Act: -0.0000

Data Index: 463280 (C4 (Web Text))

Max Activating Token Index: 535

Text #9

Max Range: 1.8610. Min Range: -1.8610

Max Act: 1.2990. Min Act: -0.0000

Data Index: 1083578 (C4 (Web Text))

Max Activating Token Index: 990

Text #10

Max Range: 1.8610. Min Range: -1.8610

Max Act: 1.2826. Min Act: -0.0000

Data Index: 682425 (C4 (Web Text))

Max Activating Token Index: 85

Text #11

Max Range: 1.8610. Min Range: -1.8610

Max Act: 1.2655. Min Act: -0.0000

Data Index: 1161031 (C4 (Web Text))

Max Activating Token Index: 17

Text #12

Max Range: 1.8610. Min Range: -1.8610

Max Act: 1.2908. Min Act: -0.0000

Data Index: 928481 (C4 (Web Text))

Max Activating Token Index: 239

Text #13

Max Range: 1.8610. Min Range: -1.8610

Max Act: 1.2423. Min Act: -0.0000

Data Index: 173249 (C4 (Web Text))

Max Activating Token Index: 779

Text #14

Max Range: 1.8610. Min Range: -1.8610

Max Act: 1.2359. Min Act: -0.0000

Data Index: 3437 (C4 (Web Text))

Max Activating Token Index: 680

Text #15

Max Range: 1.8610. Min Range: -1.8610

Max Act: 1.2628. Min Act: -0.0000

Data Index: 272301 (C4 (Web Text))

Max Activating Token Index: 621

Text #16

Max Range: 1.8610. Min Range: -1.8610

Max Act: 1.1827. Min Act: -0.0000

Data Index: 75695 (C4 (Web Text))

Max Activating Token Index: 673

Text #17

Max Range: 1.8610. Min Range: -1.8610

Max Act: 1.2538. Min Act: -0.0000

Data Index: 1282129 (C4 (Web Text))

Max Activating Token Index: 690

Text #18

Max Range: 1.8610. Min Range: -1.8610

Max Act: 1.2130. Min Act: -0.0000

Data Index: 316033 (C4 (Web Text))

Max Activating Token Index: 111

Text #19

Max Range: 1.8610. Min Range: -1.8610

Max Act: 1.2777. Min Act: -0.0000

Data Index: 30974 (C4 (Web Text))

Max Activating Token Index: 125