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

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

Neuron 541 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: 4.8772. Min Range: -4.8772

Max Act: 4.5288. Min Act: -0.0001

Data Index: 1234186 (C4 (Web Text))

Max Activating Token Index: 674

Text #1

Max Range: 4.8772. Min Range: -4.8772

Max Act: 4.4351. Min Act: -0.0001

Data Index: 844477 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 4.8772. Min Range: -4.8772

Max Act: 4.0704. Min Act: -0.0001

Data Index: 334473 (C4 (Web Text))

Max Activating Token Index: 784

Text #3

Max Range: 4.8772. Min Range: -4.8772

Max Act: 4.8772. Min Act: -0.0001

Data Index: 774839 (C4 (Web Text))

Max Activating Token Index: 727

Text #4

Max Range: 4.8772. Min Range: -4.8772

Max Act: 4.7515. Min Act: -0.0001

Data Index: 103244 (C4 (Web Text))

Max Activating Token Index: 1010

Text #5

Max Range: 4.8772. Min Range: -4.8772

Max Act: 3.9411. Min Act: -0.0001

Data Index: 437781 (C4 (Web Text))

Max Activating Token Index: 304

Text #6

Max Range: 4.8772. Min Range: -4.8772

Max Act: 3.9365. Min Act: -0.0001

Data Index: 522109 (C4 (Web Text))

Max Activating Token Index: 357

Text #7

Max Range: 4.8772. Min Range: -4.8772

Max Act: 4.7834. Min Act: -0.0001

Data Index: 1315693 (C4 (Web Text))

Max Activating Token Index: 868

Text #8

Max Range: 4.8772. Min Range: -4.8772

Max Act: 3.9012. Min Act: -0.0001

Data Index: 267439 (C4 (Web Text))

Max Activating Token Index: 960

Text #9

Max Range: 4.8772. Min Range: -4.8772

Max Act: 3.9173. Min Act: -0.0001

Data Index: 62885 (C4 (Web Text))

Max Activating Token Index: 667

Text #10

Max Range: 4.8772. Min Range: -4.8772

Max Act: 3.8163. Min Act: -0.0001

Data Index: 796870 (C4 (Web Text))

Max Activating Token Index: 768

Text #11

Max Range: 4.8772. Min Range: -4.8772

Max Act: 3.7469. Min Act: -0.0001

Data Index: 329425 (C4 (Web Text))

Max Activating Token Index: 471

Text #12

Max Range: 4.8772. Min Range: -4.8772

Max Act: 3.7410. Min Act: -0.0001

Data Index: 523426 (C4 (Web Text))

Max Activating Token Index: 639

Text #13

Max Range: 4.8772. Min Range: -4.8772

Max Act: 3.3829. Min Act: -0.0001

Data Index: 160398 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 4.8772. Min Range: -4.8772

Max Act: 3.4788. Min Act: -0.0001

Data Index: 997428 (C4 (Web Text))

Max Activating Token Index: 531

Text #15

Max Range: 4.8772. Min Range: -4.8772

Max Act: 2.9107. Min Act: -0.0001

Data Index: 471296 (C4 (Web Text))

Max Activating Token Index: 184

Text #16

Max Range: 4.8772. Min Range: -4.8772

Max Act: 3.0565. Min Act: -0.0001

Data Index: 305822 (C4 (Web Text))

Max Activating Token Index: 937

Text #17

Max Range: 4.8772. Min Range: -4.8772

Max Act: 3.6290. Min Act: -0.0001

Data Index: 24560 (C4 (Web Text))

Max Activating Token Index: 452

Text #18

Max Range: 4.8772. Min Range: -4.8772

Max Act: 2.8912. Min Act: -0.0001

Data Index: 613415 (C4 (Web Text))

Max Activating Token Index: 136

Text #19

Max Range: 4.8772. Min Range: -4.8772

Max Act: 3.7241. Min Act: -0.0001

Data Index: 480425 (C4 (Web Text))

Max Activating Token Index: 622