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

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

Neuron 162 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: 0.8612. Min Range: -0.8612

Max Act: 0.8174. Min Act: -0.0000

Data Index: 965689 (C4 (Web Text))

Max Activating Token Index: 858

Text #1

Max Range: 0.8612. Min Range: -0.8612

Max Act: 0.8612. Min Act: -0.0000

Data Index: 1280421 (C4 (Web Text))

Max Activating Token Index: 949

Text #2

Max Range: 0.8612. Min Range: -0.8612

Max Act: 0.8095. Min Act: -0.0000

Data Index: 737822 (C4 (Web Text))

Max Activating Token Index: 94

Text #3

Max Range: 0.8612. Min Range: -0.8612

Max Act: 0.8003. Min Act: -0.0000

Data Index: 657468 (C4 (Web Text))

Max Activating Token Index: 335

Text #4

Max Range: 0.8612. Min Range: -0.8612

Max Act: 0.7805. Min Act: -0.0000

Data Index: 892475 (C4 (Web Text))

Max Activating Token Index: 637

Text #5

Max Range: 0.8612. Min Range: -0.8612

Max Act: 0.7775. Min Act: -0.0000

Data Index: 648481 (C4 (Web Text))

Max Activating Token Index: 764

Text #6

Max Range: 0.8612. Min Range: -0.8612

Max Act: 0.7368. Min Act: -0.0000

Data Index: 471015 (C4 (Web Text))

Max Activating Token Index: 882

Text #7

Max Range: 0.8612. Min Range: -0.8612

Max Act: 0.7086. Min Act: -0.0000

Data Index: 211259 (C4 (Web Text))

Max Activating Token Index: 654

Text #8

Max Range: 0.8612. Min Range: -0.8612

Max Act: 0.7771. Min Act: -0.0000

Data Index: 1139162 (C4 (Web Text))

Max Activating Token Index: 524

Text #9

Max Range: 0.8612. Min Range: -0.8612

Max Act: 0.7141. Min Act: -0.0000

Data Index: 1245584 (C4 (Web Text))

Max Activating Token Index: 662

Text #10

Max Range: 0.8612. Min Range: -0.8612

Max Act: 0.7290. Min Act: -0.0000

Data Index: 411323 (C4 (Web Text))

Max Activating Token Index: 484

Text #11

Max Range: 0.8612. Min Range: -0.8612

Max Act: 0.7242. Min Act: -0.0000

Data Index: 444112 (C4 (Web Text))

Max Activating Token Index: 366

Text #12

Max Range: 0.8612. Min Range: -0.8612

Max Act: 0.6976. Min Act: -0.0000

Data Index: 1063680 (C4 (Web Text))

Max Activating Token Index: 931

Text #13

Max Range: 0.8612. Min Range: -0.8612

Max Act: 0.6897. Min Act: -0.0000

Data Index: 1141987 (C4 (Web Text))

Max Activating Token Index: 66

Text #14

Max Range: 0.8612. Min Range: -0.8612

Max Act: 0.6867. Min Act: -0.0000

Data Index: 499886 (C4 (Web Text))

Max Activating Token Index: 412

Text #15

Max Range: 0.8612. Min Range: -0.8612

Max Act: 0.7072. Min Act: -0.0000

Data Index: 324203 (C4 (Web Text))

Max Activating Token Index: 872

Text #16

Max Range: 0.8612. Min Range: -0.8612

Max Act: 0.6751. Min Act: -0.0000

Data Index: 266518 (C4 (Web Text))

Max Activating Token Index: 672

Text #17

Max Range: 0.8612. Min Range: -0.8612

Max Act: 0.6937. Min Act: -0.0000

Data Index: 258538 (C4 (Web Text))

Max Activating Token Index: 981

Text #18

Max Range: 0.8612. Min Range: -0.8612

Max Act: 0.6811. Min Act: -0.0000

Data Index: 455689 (C4 (Web Text))

Max Activating Token Index: 350

Text #19

Max Range: 0.8612. Min Range: -0.8612

Max Act: 0.6985. Min Act: -0.0000

Data Index: 1194336 (C4 (Web Text))

Max Activating Token Index: 447