Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5390 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1718. Min Range: -1.1718

Max Act: 1.0470. Min Act: -0.0000

Data Index: 356328 (C4 (Web Text))

Max Activating Token Index: 838

Text #1

Max Range: 1.1718. Min Range: -1.1718

Max Act: 1.1173. Min Act: -0.0000

Data Index: 2692 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 1.1718. Min Range: -1.1718

Max Act: 1.1718. Min Act: -0.0000

Data Index: 90638 (C4 (Web Text))

Max Activating Token Index: 290

Text #3

Max Range: 1.1718. Min Range: -1.1718

Max Act: 0.7963. Min Act: -0.0000

Data Index: 678205 (C4 (Web Text))

Max Activating Token Index: 309

Text #4

Max Range: 1.1718. Min Range: -1.1718

Max Act: 1.0079. Min Act: -0.0000

Data Index: 491877 (C4 (Web Text))

Max Activating Token Index: 110

Text #5

Max Range: 1.1718. Min Range: -1.1718

Max Act: 1.0130. Min Act: -0.0000

Data Index: 1160773 (C4 (Web Text))

Max Activating Token Index: 752

Text #6

Max Range: 1.1718. Min Range: -1.1718

Max Act: 0.8751. Min Act: -0.0000

Data Index: 558223 (C4 (Web Text))

Max Activating Token Index: 201

Text #7

Max Range: 1.1718. Min Range: -1.1718

Max Act: 0.7271. Min Act: -0.0001

Data Index: 196844 (C4 (Web Text))

Max Activating Token Index: 407

Text #8

Max Range: 1.1718. Min Range: -1.1718

Max Act: 0.7661. Min Act: -0.0000

Data Index: 809429 (C4 (Web Text))

Max Activating Token Index: 444

Text #9

Max Range: 1.1718. Min Range: -1.1718

Max Act: 0.7877. Min Act: -0.0000

Data Index: 318796 (C4 (Web Text))

Max Activating Token Index: 211

Text #10

Max Range: 1.1718. Min Range: -1.1718

Max Act: 0.7575. Min Act: -0.0000

Data Index: 736978 (C4 (Web Text))

Max Activating Token Index: 486

Text #11

Max Range: 1.1718. Min Range: -1.1718

Max Act: 0.6689. Min Act: -0.0000

Data Index: 279237 (C4 (Web Text))

Max Activating Token Index: 770

Text #12

Max Range: 1.1718. Min Range: -1.1718

Max Act: 0.6575. Min Act: -0.0000

Data Index: 1065330 (C4 (Web Text))

Max Activating Token Index: 223

Text #13

Max Range: 1.1718. Min Range: -1.1718

Max Act: 0.7995. Min Act: -0.0000

Data Index: 950342 (C4 (Web Text))

Max Activating Token Index: 317

Text #14

Max Range: 1.1718. Min Range: -1.1718

Max Act: 0.7505. Min Act: -0.0001

Data Index: 937494 (C4 (Web Text))

Max Activating Token Index: 525

Text #15

Max Range: 1.1718. Min Range: -1.1718

Max Act: 0.6525. Min Act: -0.0000

Data Index: 417169 (C4 (Web Text))

Max Activating Token Index: 170

Text #16

Max Range: 1.1718. Min Range: -1.1718

Max Act: 0.6784. Min Act: -0.0000

Data Index: 459280 (C4 (Web Text))

Max Activating Token Index: 47

Text #17

Max Range: 1.1718. Min Range: -1.1718

Max Act: 0.6876. Min Act: -0.0000

Data Index: 916436 (C4 (Web Text))

Max Activating Token Index: 796

Text #18

Max Range: 1.1718. Min Range: -1.1718

Max Act: 0.5569. Min Act: -0.0000

Data Index: 969442 (C4 (Web Text))

Max Activating Token Index: 344

Text #19

Max Range: 1.1718. Min Range: -1.1718

Max Act: 0.7554. Min Act: -0.0001

Data Index: 1016510 (C4 (Web Text))

Max Activating Token Index: 268