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

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

Neuron 3175 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0508. Min Act: -0.0001

Data Index: 182649 (C4 (Web Text))

Max Activating Token Index: 849

Text #1

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0474. Min Act: -0.0001

Data Index: 878594 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0477. Min Act: -0.0001

Data Index: 435833 (C4 (Web Text))

Max Activating Token Index: 54

Text #3

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0461. Min Act: -0.0001

Data Index: 839153 (C4 (Web Text))

Max Activating Token Index: 882

Text #4

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0460. Min Act: -0.0001

Data Index: 661379 (C4 (Web Text))

Max Activating Token Index: 342

Text #5

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0470. Min Act: -0.0001

Data Index: 835493 (C4 (Web Text))

Max Activating Token Index: 595

Text #6

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0473. Min Act: -0.0001

Data Index: 1264132 (C4 (Web Text))

Max Activating Token Index: 565

Text #7

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0462. Min Act: -0.0001

Data Index: 1260999 (C4 (Web Text))

Max Activating Token Index: 878

Text #8

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0462. Min Act: -0.0001

Data Index: 296671 (C4 (Web Text))

Max Activating Token Index: 935

Text #9

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0453. Min Act: -0.0001

Data Index: 1046889 (C4 (Web Text))

Max Activating Token Index: 660

Text #10

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0457. Min Act: -0.0001

Data Index: 232391 (C4 (Web Text))

Max Activating Token Index: 143

Text #11

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0468. Min Act: -0.0001

Data Index: 1176212 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0460. Min Act: -0.0001

Data Index: 397426 (C4 (Web Text))

Max Activating Token Index: 66

Text #13

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0451. Min Act: -0.0001

Data Index: 492988 (C4 (Web Text))

Max Activating Token Index: 92

Text #14

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0449. Min Act: -0.0001

Data Index: 861123 (C4 (Web Text))

Max Activating Token Index: 268

Text #15

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0457. Min Act: -0.0001

Data Index: 1222344 (C4 (Web Text))

Max Activating Token Index: 19

Text #16

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0445. Min Act: -0.0001

Data Index: 268945 (C4 (Web Text))

Max Activating Token Index: 32

Text #17

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0447. Min Act: -0.0001

Data Index: 1139989 (C4 (Web Text))

Max Activating Token Index: 1001

Text #18

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0452. Min Act: -0.0001

Data Index: 1190801 (C4 (Web Text))

Max Activating Token Index: 20

Text #19

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0457. Min Act: -0.0001

Data Index: 829965 (C4 (Web Text))

Max Activating Token Index: 68