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

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

Neuron 5119 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1673. Min Range: -3.1673

Max Act: 3.1673. Min Act: -0.0000

Data Index: 388684 (C4 (Web Text))

Max Activating Token Index: 714

Text #1

Max Range: 3.1673. Min Range: -3.1673

Max Act: 3.1193. Min Act: -0.0000

Data Index: 385391 (C4 (Web Text))

Max Activating Token Index: 68

Text #2

Max Range: 3.1673. Min Range: -3.1673

Max Act: 2.7746. Min Act: -0.0000

Data Index: 809673 (C4 (Web Text))

Max Activating Token Index: 341

Text #3

Max Range: 3.1673. Min Range: -3.1673

Max Act: 2.8415. Min Act: -0.0000

Data Index: 1023182 (C4 (Web Text))

Max Activating Token Index: 61

Text #4

Max Range: 3.1673. Min Range: -3.1673

Max Act: 2.7021. Min Act: -0.0000

Data Index: 785066 (C4 (Web Text))

Max Activating Token Index: 33

Text #5

Max Range: 3.1673. Min Range: -3.1673

Max Act: 2.5595. Min Act: -0.0000

Data Index: 582630 (C4 (Web Text))

Max Activating Token Index: 704

Text #6

Max Range: 3.1673. Min Range: -3.1673

Max Act: 2.5556. Min Act: -0.0000

Data Index: 214948 (C4 (Web Text))

Max Activating Token Index: 630

Text #7

Max Range: 3.1673. Min Range: -3.1673

Max Act: 2.4883. Min Act: -0.0000

Data Index: 1286619 (C4 (Web Text))

Max Activating Token Index: 30

Text #8

Max Range: 3.1673. Min Range: -3.1673

Max Act: 2.4791. Min Act: -0.0001

Data Index: 211367 (C4 (Web Text))

Max Activating Token Index: 388

Text #9

Max Range: 3.1673. Min Range: -3.1673

Max Act: 2.4831. Min Act: -0.0000

Data Index: 272118 (C4 (Web Text))

Max Activating Token Index: 700

Text #10

Max Range: 3.1673. Min Range: -3.1673

Max Act: 2.3458. Min Act: -0.0000

Data Index: 500034 (C4 (Web Text))

Max Activating Token Index: 603

Text #11

Max Range: 3.1673. Min Range: -3.1673

Max Act: 2.3421. Min Act: -0.0000

Data Index: 761285 (C4 (Web Text))

Max Activating Token Index: 697

Text #12

Max Range: 3.1673. Min Range: -3.1673

Max Act: 2.2560. Min Act: -0.0000

Data Index: 51212 (C4 (Web Text))

Max Activating Token Index: 963

Text #13

Max Range: 3.1673. Min Range: -3.1673

Max Act: 2.2401. Min Act: -0.0000

Data Index: 789908 (C4 (Web Text))

Max Activating Token Index: 945

Text #14

Max Range: 3.1673. Min Range: -3.1673

Max Act: 2.3158. Min Act: -0.0001

Data Index: 962691 (C4 (Web Text))

Max Activating Token Index: 318

Text #15

Max Range: 3.1673. Min Range: -3.1673

Max Act: 2.1731. Min Act: -0.0000

Data Index: 715109 (C4 (Web Text))

Max Activating Token Index: 848

Text #16

Max Range: 3.1673. Min Range: -3.1673

Max Act: 2.0991. Min Act: -0.0000

Data Index: 1028441 (C4 (Web Text))

Max Activating Token Index: 100

Text #17

Max Range: 3.1673. Min Range: -3.1673

Max Act: 2.2892. Min Act: -0.0000

Data Index: 1140127 (C4 (Web Text))

Max Activating Token Index: 406

Text #18

Max Range: 3.1673. Min Range: -3.1673

Max Act: 2.2828. Min Act: -0.0000

Data Index: 620552 (C4 (Web Text))

Max Activating Token Index: 382

Text #19

Max Range: 3.1673. Min Range: -3.1673

Max Act: 2.1575. Min Act: -0.0000

Data Index: 371056 (C4 (Web Text))

Max Activating Token Index: 813