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

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

Neuron 1648 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7336. Min Range: -1.7336

Max Act: 1.7336. Min Act: 0.0001

Data Index: 1645885 (Python Code)

Max Activating Token Index: 844

Text #1

Max Range: 1.7336. Min Range: -1.7336

Max Act: 1.6496. Min Act: -0.0000

Data Index: 1622632 (Python Code)

Max Activating Token Index: 193

Text #2

Max Range: 1.7336. Min Range: -1.7336

Max Act: 1.5028. Min Act: -0.0000

Data Index: 1380409 (Python Code)

Max Activating Token Index: 23

Text #3

Max Range: 1.7336. Min Range: -1.7336

Max Act: 1.5786. Min Act: -0.0000

Data Index: 1636310 (Python Code)

Max Activating Token Index: 118

Text #4

Max Range: 1.7336. Min Range: -1.7336

Max Act: 1.5832. Min Act: -0.0000

Data Index: 1524507 (Python Code)

Max Activating Token Index: 871

Text #5

Max Range: 1.7336. Min Range: -1.7336

Max Act: 1.4229. Min Act: -0.0000

Data Index: 1396723 (Python Code)

Max Activating Token Index: 728

Text #6

Max Range: 1.7336. Min Range: -1.7336

Max Act: 1.4318. Min Act: -0.0000

Data Index: 1618966 (Python Code)

Max Activating Token Index: 123

Text #7

Max Range: 1.7336. Min Range: -1.7336

Max Act: 1.4506. Min Act: -0.0000

Data Index: 1379071 (Python Code)

Max Activating Token Index: 524

Text #8

Max Range: 1.7336. Min Range: -1.7336

Max Act: 1.4059. Min Act: -0.0000

Data Index: 1567647 (Python Code)

Max Activating Token Index: 566

Text #9

Max Range: 1.7336. Min Range: -1.7336

Max Act: 1.3462. Min Act: -0.0000

Data Index: 1650173 (Python Code)

Max Activating Token Index: 555

Text #10

Max Range: 1.7336. Min Range: -1.7336

Max Act: 1.3472. Min Act: 0.0001

Data Index: 1545003 (Python Code)

Max Activating Token Index: 174

Text #11

Max Range: 1.7336. Min Range: -1.7336

Max Act: 1.3771. Min Act: -0.0000

Data Index: 1609210 (Python Code)

Max Activating Token Index: 30

Text #12

Max Range: 1.7336. Min Range: -1.7336

Max Act: 1.3677. Min Act: 0.0000

Data Index: 1543304 (Python Code)

Max Activating Token Index: 577

Text #13

Max Range: 1.7336. Min Range: -1.7336

Max Act: 1.3407. Min Act: -0.0000

Data Index: 1512637 (Python Code)

Max Activating Token Index: 344

Text #14

Max Range: 1.7336. Min Range: -1.7336

Max Act: 1.4730. Min Act: -0.0000

Data Index: 1472447 (Python Code)

Max Activating Token Index: 826

Text #15

Max Range: 1.7336. Min Range: -1.7336

Max Act: 1.3479. Min Act: -0.0000

Data Index: 1394294 (Python Code)

Max Activating Token Index: 197

Text #16

Max Range: 1.7336. Min Range: -1.7336

Max Act: 1.3047. Min Act: -0.0000

Data Index: 1656021 (Python Code)

Max Activating Token Index: 253

Text #17

Max Range: 1.7336. Min Range: -1.7336

Max Act: 1.2963. Min Act: -0.0000

Data Index: 1620420 (Python Code)

Max Activating Token Index: 550

Text #18

Max Range: 1.7336. Min Range: -1.7336

Max Act: 1.2714. Min Act: -0.0000

Data Index: 1602179 (Python Code)

Max Activating Token Index: 203

Text #19

Max Range: 1.7336. Min Range: -1.7336

Max Act: 1.2925. Min Act: -0.0000

Data Index: 1572379 (Python Code)

Max Activating Token Index: 681