Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1476 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7115. Min Range: -0.7115

Max Act: 0.7115. Min Act: -0.0003

Data Index: 1009310 (C4 (Web Text))

Max Activating Token Index: 81

Text #1

Max Range: 0.7115. Min Range: -0.7115

Max Act: 0.6570. Min Act: -0.0003

Data Index: 393195 (C4 (Web Text))

Max Activating Token Index: 99

Text #2

Max Range: 0.7115. Min Range: -0.7115

Max Act: 0.6420. Min Act: -0.0003

Data Index: 112445 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 0.7115. Min Range: -0.7115

Max Act: 0.6068. Min Act: -0.0003

Data Index: 387716 (C4 (Web Text))

Max Activating Token Index: 895

Text #4

Max Range: 0.7115. Min Range: -0.7115

Max Act: 0.5655. Min Act: -0.0003

Data Index: 379962 (C4 (Web Text))

Max Activating Token Index: 886

Text #5

Max Range: 0.7115. Min Range: -0.7115

Max Act: 0.5733. Min Act: -0.0003

Data Index: 97443 (C4 (Web Text))

Max Activating Token Index: 612

Text #6

Max Range: 0.7115. Min Range: -0.7115

Max Act: 0.5705. Min Act: -0.0003

Data Index: 1344398 (C4 (Web Text))

Max Activating Token Index: 243

Text #7

Max Range: 0.7115. Min Range: -0.7115

Max Act: 0.5622. Min Act: -0.0003

Data Index: 1341399 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 0.7115. Min Range: -0.7115

Max Act: 0.5963. Min Act: -0.0003

Data Index: 16106 (C4 (Web Text))

Max Activating Token Index: 10

Text #9

Max Range: 0.7115. Min Range: -0.7115

Max Act: 0.5949. Min Act: -0.0003

Data Index: 22771 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 0.7115. Min Range: -0.7115

Max Act: 0.5910. Min Act: -0.0003

Data Index: 1053100 (C4 (Web Text))

Max Activating Token Index: 8

Text #11

Max Range: 0.7115. Min Range: -0.7115

Max Act: 0.5372. Min Act: -0.0003

Data Index: 1091160 (C4 (Web Text))

Max Activating Token Index: 45

Text #12

Max Range: 0.7115. Min Range: -0.7115

Max Act: 0.5528. Min Act: -0.0003

Data Index: 252323 (C4 (Web Text))

Max Activating Token Index: 55

Text #13

Max Range: 0.7115. Min Range: -0.7115

Max Act: 0.5651. Min Act: -0.0003

Data Index: 244465 (C4 (Web Text))

Max Activating Token Index: 57

Text #14

Max Range: 0.7115. Min Range: -0.7115

Max Act: 0.5487. Min Act: -0.0003

Data Index: 163251 (C4 (Web Text))

Max Activating Token Index: 67

Text #15

Max Range: 0.7115. Min Range: -0.7115

Max Act: 0.5670. Min Act: -0.0003

Data Index: 332434 (C4 (Web Text))

Max Activating Token Index: 51

Text #16

Max Range: 0.7115. Min Range: -0.7115

Max Act: 0.5662. Min Act: -0.0003

Data Index: 682808 (C4 (Web Text))

Max Activating Token Index: 57

Text #17

Max Range: 0.7115. Min Range: -0.7115

Max Act: 0.5813. Min Act: -0.0003

Data Index: 433290 (C4 (Web Text))

Max Activating Token Index: 2

Text #18

Max Range: 0.7115. Min Range: -0.7115

Max Act: 0.5813. Min Act: -0.0003

Data Index: 192441 (C4 (Web Text))

Max Activating Token Index: 2

Text #19

Max Range: 0.7115. Min Range: -0.7115

Max Act: 0.5652. Min Act: -0.0003

Data Index: 781963 (C4 (Web Text))

Max Activating Token Index: 6