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

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

Neuron 4253 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.8433. Min Act: -0.0000

Data Index: 943112 (C4 (Web Text))

Max Activating Token Index: 680

Text #1

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.5664. Min Act: -0.0000

Data Index: 1464337 (Python Code)

Max Activating Token Index: 155

Text #2

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.5057. Min Act: -0.0000

Data Index: 885000 (C4 (Web Text))

Max Activating Token Index: 349

Text #3

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.5026. Min Act: -0.0000

Data Index: 430815 (C4 (Web Text))

Max Activating Token Index: 165

Text #4

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.4881. Min Act: -0.0000

Data Index: 242015 (C4 (Web Text))

Max Activating Token Index: 798

Text #5

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.4727. Min Act: -0.0000

Data Index: 881662 (C4 (Web Text))

Max Activating Token Index: 562

Text #6

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.4285. Min Act: -0.0000

Data Index: 565574 (C4 (Web Text))

Max Activating Token Index: 779

Text #7

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.4869. Min Act: -0.0000

Data Index: 1550826 (Python Code)

Max Activating Token Index: 101

Text #8

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.4614. Min Act: -0.0000

Data Index: 606621 (C4 (Web Text))

Max Activating Token Index: 589

Text #9

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.4556. Min Act: -0.0000

Data Index: 52852 (C4 (Web Text))

Max Activating Token Index: 120

Text #10

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.4692. Min Act: -0.0000

Data Index: 1073792 (C4 (Web Text))

Max Activating Token Index: 931

Text #11

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.4570. Min Act: -0.0000

Data Index: 461356 (C4 (Web Text))

Max Activating Token Index: 629

Text #12

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.4509. Min Act: -0.0000

Data Index: 1279717 (C4 (Web Text))

Max Activating Token Index: 513

Text #13

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.4483. Min Act: -0.0000

Data Index: 226064 (C4 (Web Text))

Max Activating Token Index: 835

Text #14

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.4633. Min Act: -0.0000

Data Index: 764313 (C4 (Web Text))

Max Activating Token Index: 982

Text #15

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.4614. Min Act: -0.0000

Data Index: 742225 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.4423. Min Act: -0.0000

Data Index: 98358 (C4 (Web Text))

Max Activating Token Index: 735

Text #17

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.4365. Min Act: -0.0000

Data Index: 944115 (C4 (Web Text))

Max Activating Token Index: 388

Text #18

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.4610. Min Act: -0.0000

Data Index: 1600015 (Python Code)

Max Activating Token Index: 773

Text #19

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.4420. Min Act: -0.0000

Data Index: 1444718 (Python Code)

Max Activating Token Index: 612