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

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

Neuron 35 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: 2.0391. Min Range: -2.0391

Max Act: 2.0391. Min Act: -0.0000

Data Index: 188860 (C4 (Web Text))

Max Activating Token Index: 536

Text #1

Max Range: 2.0391. Min Range: -2.0391

Max Act: 1.8815. Min Act: -0.0000

Data Index: 138161 (C4 (Web Text))

Max Activating Token Index: 178

Text #2

Max Range: 2.0391. Min Range: -2.0391

Max Act: 1.6211. Min Act: -0.0000

Data Index: 640395 (C4 (Web Text))

Max Activating Token Index: 55

Text #3

Max Range: 2.0391. Min Range: -2.0391

Max Act: 1.2144. Min Act: 0.0000

Data Index: 869067 (C4 (Web Text))

Max Activating Token Index: 832

Text #4

Max Range: 2.0391. Min Range: -2.0391

Max Act: 1.4637. Min Act: -0.0000

Data Index: 1271217 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 2.0391. Min Range: -2.0391

Max Act: 1.3372. Min Act: -0.0000

Data Index: 537730 (C4 (Web Text))

Max Activating Token Index: 761

Text #6

Max Range: 2.0391. Min Range: -2.0391

Max Act: 1.2997. Min Act: -0.0000

Data Index: 1300553 (C4 (Web Text))

Max Activating Token Index: 87

Text #7

Max Range: 2.0391. Min Range: -2.0391

Max Act: 1.3673. Min Act: -0.0000

Data Index: 424285 (C4 (Web Text))

Max Activating Token Index: 398

Text #8

Max Range: 2.0391. Min Range: -2.0391

Max Act: 1.2936. Min Act: -0.0000

Data Index: 997631 (C4 (Web Text))

Max Activating Token Index: 709

Text #9

Max Range: 2.0391. Min Range: -2.0391

Max Act: 1.3061. Min Act: -0.0000

Data Index: 1297416 (C4 (Web Text))

Max Activating Token Index: 740

Text #10

Max Range: 2.0391. Min Range: -2.0391

Max Act: 1.3736. Min Act: -0.0000

Data Index: 989045 (C4 (Web Text))

Max Activating Token Index: 521

Text #11

Max Range: 2.0391. Min Range: -2.0391

Max Act: 1.2989. Min Act: -0.0000

Data Index: 749298 (C4 (Web Text))

Max Activating Token Index: 48

Text #12

Max Range: 2.0391. Min Range: -2.0391

Max Act: 1.1881. Min Act: -0.0000

Data Index: 1229994 (C4 (Web Text))

Max Activating Token Index: 459

Text #13

Max Range: 2.0391. Min Range: -2.0391

Max Act: 1.2513. Min Act: -0.0000

Data Index: 910820 (C4 (Web Text))

Max Activating Token Index: 15

Text #14

Max Range: 2.0391. Min Range: -2.0391

Max Act: 1.2113. Min Act: -0.0000

Data Index: 1171585 (C4 (Web Text))

Max Activating Token Index: 702

Text #15

Max Range: 2.0391. Min Range: -2.0391

Max Act: 1.1956. Min Act: -0.0000

Data Index: 1124612 (C4 (Web Text))

Max Activating Token Index: 880

Text #16

Max Range: 2.0391. Min Range: -2.0391

Max Act: 1.2398. Min Act: -0.0000

Data Index: 1188989 (C4 (Web Text))

Max Activating Token Index: 679

Text #17

Max Range: 2.0391. Min Range: -2.0391

Max Act: 1.1568. Min Act: -0.0000

Data Index: 66554 (C4 (Web Text))

Max Activating Token Index: 636

Text #18

Max Range: 2.0391. Min Range: -2.0391

Max Act: 1.1542. Min Act: -0.0000

Data Index: 1267973 (C4 (Web Text))

Max Activating Token Index: 899

Text #19

Max Range: 2.0391. Min Range: -2.0391

Max Act: 1.1538. Min Act: -0.0000

Data Index: 133009 (C4 (Web Text))

Max Activating Token Index: 746