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

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

Neuron 3740 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5016. Min Range: -2.5016

Max Act: 2.5016. Min Act: -0.0000

Data Index: 277250 (C4 (Web Text))

Max Activating Token Index: 28

Text #1

Max Range: 2.5016. Min Range: -2.5016

Max Act: 2.0027. Min Act: -0.0000

Data Index: 1049 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 2.5016. Min Range: -2.5016

Max Act: 1.9262. Min Act: -0.0000

Data Index: 577077 (C4 (Web Text))

Max Activating Token Index: 698

Text #3

Max Range: 2.5016. Min Range: -2.5016

Max Act: 1.7881. Min Act: -0.0000

Data Index: 22116 (C4 (Web Text))

Max Activating Token Index: 901

Text #4

Max Range: 2.5016. Min Range: -2.5016

Max Act: 1.8207. Min Act: -0.0000

Data Index: 954539 (C4 (Web Text))

Max Activating Token Index: 141

Text #5

Max Range: 2.5016. Min Range: -2.5016

Max Act: 1.7037. Min Act: -0.0000

Data Index: 1255096 (C4 (Web Text))

Max Activating Token Index: 923

Text #6

Max Range: 2.5016. Min Range: -2.5016

Max Act: 1.7883. Min Act: -0.0000

Data Index: 1338334 (C4 (Web Text))

Max Activating Token Index: 155

Text #7

Max Range: 2.5016. Min Range: -2.5016

Max Act: 1.8783. Min Act: -0.0000

Data Index: 1358180 (C4 (Web Text))

Max Activating Token Index: 773

Text #8

Max Range: 2.5016. Min Range: -2.5016

Max Act: 1.8439. Min Act: -0.0000

Data Index: 152662 (C4 (Web Text))

Max Activating Token Index: 435

Text #9

Max Range: 2.5016. Min Range: -2.5016

Max Act: 1.8497. Min Act: -0.0000

Data Index: 642013 (C4 (Web Text))

Max Activating Token Index: 288

Text #10

Max Range: 2.5016. Min Range: -2.5016

Max Act: 1.7800. Min Act: -0.0000

Data Index: 1284939 (C4 (Web Text))

Max Activating Token Index: 611

Text #11

Max Range: 2.5016. Min Range: -2.5016

Max Act: 1.6668. Min Act: -0.0000

Data Index: 208741 (C4 (Web Text))

Max Activating Token Index: 1022

Text #12

Max Range: 2.5016. Min Range: -2.5016

Max Act: 1.5415. Min Act: -0.0000

Data Index: 1289515 (C4 (Web Text))

Max Activating Token Index: 853

Text #13

Max Range: 2.5016. Min Range: -2.5016

Max Act: 1.6893. Min Act: -0.0000

Data Index: 106660 (C4 (Web Text))

Max Activating Token Index: 78

Text #14

Max Range: 2.5016. Min Range: -2.5016

Max Act: 1.5829. Min Act: -0.0000

Data Index: 1141824 (C4 (Web Text))

Max Activating Token Index: 372

Text #15

Max Range: 2.5016. Min Range: -2.5016

Max Act: 1.5813. Min Act: -0.0000

Data Index: 625619 (C4 (Web Text))

Max Activating Token Index: 467

Text #16

Max Range: 2.5016. Min Range: -2.5016

Max Act: 1.5880. Min Act: -0.0000

Data Index: 1252213 (C4 (Web Text))

Max Activating Token Index: 640

Text #17

Max Range: 2.5016. Min Range: -2.5016

Max Act: 1.5609. Min Act: -0.0000

Data Index: 916042 (C4 (Web Text))

Max Activating Token Index: 195

Text #18

Max Range: 2.5016. Min Range: -2.5016

Max Act: 1.5654. Min Act: -0.0000

Data Index: 408740 (C4 (Web Text))

Max Activating Token Index: 824

Text #19

Max Range: 2.5016. Min Range: -2.5016

Max Act: 1.4533. Min Act: -0.0000

Data Index: 920144 (C4 (Web Text))

Max Activating Token Index: 801