Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3912 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6437. Min Range: -0.6437

Max Act: 0.6264. Min Act: -0.0001

Data Index: 1500160 (Python Code)

Max Activating Token Index: 780

Text #1

Max Range: 0.6437. Min Range: -0.6437

Max Act: 0.6437. Min Act: -0.0000

Data Index: 1521074 (Python Code)

Max Activating Token Index: 148

Text #2

Max Range: 0.6437. Min Range: -0.6437

Max Act: 0.6055. Min Act: -0.0001

Data Index: 1391526 (Python Code)

Max Activating Token Index: 495

Text #3

Max Range: 0.6437. Min Range: -0.6437

Max Act: 0.5733. Min Act: -0.0001

Data Index: 1425610 (Python Code)

Max Activating Token Index: 386

Text #4

Max Range: 0.6437. Min Range: -0.6437

Max Act: 0.5715. Min Act: -0.0001

Data Index: 1371882 (Python Code)

Max Activating Token Index: 562

Text #5

Max Range: 0.6437. Min Range: -0.6437

Max Act: 0.5459. Min Act: -0.0001

Data Index: 1466648 (Python Code)

Max Activating Token Index: 364

Text #6

Max Range: 0.6437. Min Range: -0.6437

Max Act: 0.5412. Min Act: -0.0000

Data Index: 1504904 (Python Code)

Max Activating Token Index: 826

Text #7

Max Range: 0.6437. Min Range: -0.6437

Max Act: 0.5713. Min Act: -0.0001

Data Index: 1444556 (Python Code)

Max Activating Token Index: 607

Text #8

Max Range: 0.6437. Min Range: -0.6437

Max Act: 0.5569. Min Act: -0.0000

Data Index: 1630922 (Python Code)

Max Activating Token Index: 289

Text #9

Max Range: 0.6437. Min Range: -0.6437

Max Act: 0.4986. Min Act: -0.0001

Data Index: 1529555 (Python Code)

Max Activating Token Index: 754

Text #10

Max Range: 0.6437. Min Range: -0.6437

Max Act: 0.5117. Min Act: -0.0000

Data Index: 1384852 (Python Code)

Max Activating Token Index: 648

Text #11

Max Range: 0.6437. Min Range: -0.6437

Max Act: 0.4907. Min Act: -0.0000

Data Index: 1439797 (Python Code)

Max Activating Token Index: 424

Text #12

Max Range: 0.6437. Min Range: -0.6437

Max Act: 0.5050. Min Act: -0.0000

Data Index: 1441257 (Python Code)

Max Activating Token Index: 286

Text #13

Max Range: 0.6437. Min Range: -0.6437

Max Act: 0.5215. Min Act: -0.0000

Data Index: 1509102 (Python Code)

Max Activating Token Index: 762

Text #14

Max Range: 0.6437. Min Range: -0.6437

Max Act: 0.5053. Min Act: -0.0001

Data Index: 1516314 (Python Code)

Max Activating Token Index: 353

Text #15

Max Range: 0.6437. Min Range: -0.6437

Max Act: 0.5001. Min Act: -0.0001

Data Index: 1559125 (Python Code)

Max Activating Token Index: 455

Text #16

Max Range: 0.6437. Min Range: -0.6437

Max Act: 0.5143. Min Act: -0.0000

Data Index: 1424498 (Python Code)

Max Activating Token Index: 376

Text #17

Max Range: 0.6437. Min Range: -0.6437

Max Act: 0.4995. Min Act: -0.0000

Data Index: 1486780 (Python Code)

Max Activating Token Index: 260

Text #18

Max Range: 0.6437. Min Range: -0.6437

Max Act: 0.4910. Min Act: -0.0000

Data Index: 1594480 (Python Code)

Max Activating Token Index: 855

Text #19

Max Range: 0.6437. Min Range: -0.6437

Max Act: 0.4898. Min Act: -0.0000

Data Index: 1375234 (Python Code)

Max Activating Token Index: 516