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

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

Neuron 3243 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0525. Min Range: -1.0525

Max Act: 1.0525. Min Act: -0.0001

Data Index: 1551720 (Python Code)

Max Activating Token Index: 640

Text #1

Max Range: 1.0525. Min Range: -1.0525

Max Act: 0.9217. Min Act: -0.0001

Data Index: 1463848 (Python Code)

Max Activating Token Index: 537

Text #2

Max Range: 1.0525. Min Range: -1.0525

Max Act: 0.9044. Min Act: -0.0001

Data Index: 1504194 (Python Code)

Max Activating Token Index: 489

Text #3

Max Range: 1.0525. Min Range: -1.0525

Max Act: 0.7367. Min Act: -0.0001

Data Index: 1403099 (Python Code)

Max Activating Token Index: 221

Text #4

Max Range: 1.0525. Min Range: -1.0525

Max Act: 0.7354. Min Act: -0.0001

Data Index: 1454321 (Python Code)

Max Activating Token Index: 632

Text #5

Max Range: 1.0525. Min Range: -1.0525

Max Act: 0.6946. Min Act: -0.0001

Data Index: 1529694 (Python Code)

Max Activating Token Index: 64

Text #6

Max Range: 1.0525. Min Range: -1.0525

Max Act: 0.7086. Min Act: -0.0001

Data Index: 1498439 (Python Code)

Max Activating Token Index: 728

Text #7

Max Range: 1.0525. Min Range: -1.0525

Max Act: 0.7724. Min Act: -0.0001

Data Index: 1405718 (Python Code)

Max Activating Token Index: 988

Text #8

Max Range: 1.0525. Min Range: -1.0525

Max Act: 0.7433. Min Act: -0.0001

Data Index: 1492627 (Python Code)

Max Activating Token Index: 635

Text #9

Max Range: 1.0525. Min Range: -1.0525

Max Act: 0.7140. Min Act: -0.0001

Data Index: 1629239 (Python Code)

Max Activating Token Index: 810

Text #10

Max Range: 1.0525. Min Range: -1.0525

Max Act: 0.7316. Min Act: -0.0001

Data Index: 1402246 (Python Code)

Max Activating Token Index: 302

Text #11

Max Range: 1.0525. Min Range: -1.0525

Max Act: 0.6829. Min Act: -0.0001

Data Index: 1566440 (Python Code)

Max Activating Token Index: 149

Text #12

Max Range: 1.0525. Min Range: -1.0525

Max Act: 0.6507. Min Act: -0.0001

Data Index: 1462145 (Python Code)

Max Activating Token Index: 846

Text #13

Max Range: 1.0525. Min Range: -1.0525

Max Act: 0.6700. Min Act: -0.0001

Data Index: 1412422 (Python Code)

Max Activating Token Index: 211

Text #14

Max Range: 1.0525. Min Range: -1.0525

Max Act: 0.6929. Min Act: -0.0001

Data Index: 1633393 (Python Code)

Max Activating Token Index: 462

Text #15

Max Range: 1.0525. Min Range: -1.0525

Max Act: 0.6584. Min Act: -0.0001

Data Index: 1527398 (Python Code)

Max Activating Token Index: 352

Text #16

Max Range: 1.0525. Min Range: -1.0525

Max Act: 0.6550. Min Act: -0.0001

Data Index: 1388321 (Python Code)

Max Activating Token Index: 304

Text #17

Max Range: 1.0525. Min Range: -1.0525

Max Act: 0.6282. Min Act: -0.0001

Data Index: 1655323 (Python Code)

Max Activating Token Index: 438

Text #18

Max Range: 1.0525. Min Range: -1.0525

Max Act: 0.6381. Min Act: -0.0001

Data Index: 463986 (C4 (Web Text))

Max Activating Token Index: 681

Text #19

Max Range: 1.0525. Min Range: -1.0525

Max Act: 0.6187. Min Act: -0.0001

Data Index: 1426850 (Python Code)

Max Activating Token Index: 254