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

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

Neuron 3459 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7997. Min Range: -0.7997

Max Act: 0.7997. Min Act: -0.0000

Data Index: 963059 (C4 (Web Text))

Max Activating Token Index: 966

Text #1

Max Range: 0.7997. Min Range: -0.7997

Max Act: 0.6895. Min Act: -0.0000

Data Index: 1206465 (C4 (Web Text))

Max Activating Token Index: 443

Text #2

Max Range: 0.7997. Min Range: -0.7997

Max Act: 0.6664. Min Act: 0.0000

Data Index: 15710 (C4 (Web Text))

Max Activating Token Index: 295

Text #3

Max Range: 0.7997. Min Range: -0.7997

Max Act: 0.6215. Min Act: -0.0000

Data Index: 154465 (C4 (Web Text))

Max Activating Token Index: 598

Text #4

Max Range: 0.7997. Min Range: -0.7997

Max Act: 0.6584. Min Act: -0.0000

Data Index: 535993 (C4 (Web Text))

Max Activating Token Index: 145

Text #5

Max Range: 0.7997. Min Range: -0.7997

Max Act: 0.7033. Min Act: -0.0000

Data Index: 487388 (C4 (Web Text))

Max Activating Token Index: 198

Text #6

Max Range: 0.7997. Min Range: -0.7997

Max Act: 0.6067. Min Act: -0.0000

Data Index: 1473588 (Python Code)

Max Activating Token Index: 580

Text #7

Max Range: 0.7997. Min Range: -0.7997

Max Act: 0.6091. Min Act: -0.0000

Data Index: 104971 (C4 (Web Text))

Max Activating Token Index: 436

Text #8

Max Range: 0.7997. Min Range: -0.7997

Max Act: 0.6105. Min Act: -0.0000

Data Index: 838975 (C4 (Web Text))

Max Activating Token Index: 1002

Text #9

Max Range: 0.7997. Min Range: -0.7997

Max Act: 0.5666. Min Act: -0.0000

Data Index: 1018266 (C4 (Web Text))

Max Activating Token Index: 861

Text #10

Max Range: 0.7997. Min Range: -0.7997

Max Act: 0.5595. Min Act: -0.0000

Data Index: 283640 (C4 (Web Text))

Max Activating Token Index: 206

Text #11

Max Range: 0.7997. Min Range: -0.7997

Max Act: 0.5281. Min Act: -0.0000

Data Index: 575845 (C4 (Web Text))

Max Activating Token Index: 227

Text #12

Max Range: 0.7997. Min Range: -0.7997

Max Act: 0.5032. Min Act: -0.0000

Data Index: 838535 (C4 (Web Text))

Max Activating Token Index: 674

Text #13

Max Range: 0.7997. Min Range: -0.7997

Max Act: 0.3741. Min Act: -0.0000

Data Index: 75757 (C4 (Web Text))

Max Activating Token Index: 798

Text #14

Max Range: 0.7997. Min Range: -0.7997

Max Act: 0.4978. Min Act: -0.0000

Data Index: 600110 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 0.7997. Min Range: -0.7997

Max Act: 0.4850. Min Act: 0.0000

Data Index: 1115873 (C4 (Web Text))

Max Activating Token Index: 634

Text #16

Max Range: 0.7997. Min Range: -0.7997

Max Act: 0.4408. Min Act: -0.0000

Data Index: 428849 (C4 (Web Text))

Max Activating Token Index: 632

Text #17

Max Range: 0.7997. Min Range: -0.7997

Max Act: 0.4299. Min Act: -0.0000

Data Index: 636804 (C4 (Web Text))

Max Activating Token Index: 930

Text #18

Max Range: 0.7997. Min Range: -0.7997

Max Act: 0.4468. Min Act: -0.0000

Data Index: 761580 (C4 (Web Text))

Max Activating Token Index: 165

Text #19

Max Range: 0.7997. Min Range: -0.7997

Max Act: 0.4525. Min Act: -0.0000

Data Index: 60690 (C4 (Web Text))

Max Activating Token Index: 676