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

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

Neuron 1675 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: 0.6274. Min Range: -0.6274

Max Act: 0.6274. Min Act: -0.0001

Data Index: 1542519 (Python Code)

Max Activating Token Index: 712

Text #1

Max Range: 0.6274. Min Range: -0.6274

Max Act: 0.5475. Min Act: -0.0000

Data Index: 1493817 (Python Code)

Max Activating Token Index: 1014

Text #2

Max Range: 0.6274. Min Range: -0.6274

Max Act: 0.5749. Min Act: -0.0000

Data Index: 1428146 (Python Code)

Max Activating Token Index: 584

Text #3

Max Range: 0.6274. Min Range: -0.6274

Max Act: 0.5287. Min Act: -0.0001

Data Index: 1637658 (Python Code)

Max Activating Token Index: 339

Text #4

Max Range: 0.6274. Min Range: -0.6274

Max Act: 0.5173. Min Act: -0.0000

Data Index: 1433210 (Python Code)

Max Activating Token Index: 28

Text #5

Max Range: 0.6274. Min Range: -0.6274

Max Act: 0.5150. Min Act: -0.0000

Data Index: 1367153 (Python Code)

Max Activating Token Index: 124

Text #6

Max Range: 0.6274. Min Range: -0.6274

Max Act: 0.5084. Min Act: -0.0000

Data Index: 1438566 (Python Code)

Max Activating Token Index: 263

Text #7

Max Range: 0.6274. Min Range: -0.6274

Max Act: 0.5065. Min Act: -0.0001

Data Index: 1486205 (Python Code)

Max Activating Token Index: 348

Text #8

Max Range: 0.6274. Min Range: -0.6274

Max Act: 0.4709. Min Act: -0.0000

Data Index: 1610722 (Python Code)

Max Activating Token Index: 729

Text #9

Max Range: 0.6274. Min Range: -0.6274

Max Act: 0.5018. Min Act: -0.0000

Data Index: 1429599 (Python Code)

Max Activating Token Index: 810

Text #10

Max Range: 0.6274. Min Range: -0.6274

Max Act: 0.4971. Min Act: -0.0000

Data Index: 1621670 (Python Code)

Max Activating Token Index: 325

Text #11

Max Range: 0.6274. Min Range: -0.6274

Max Act: 0.4956. Min Act: -0.0000

Data Index: 1471951 (Python Code)

Max Activating Token Index: 293

Text #12

Max Range: 0.6274. Min Range: -0.6274

Max Act: 0.4805. Min Act: -0.0000

Data Index: 1421005 (Python Code)

Max Activating Token Index: 15

Text #13

Max Range: 0.6274. Min Range: -0.6274

Max Act: 0.4942. Min Act: -0.0000

Data Index: 1378073 (Python Code)

Max Activating Token Index: 70

Text #14

Max Range: 0.6274. Min Range: -0.6274

Max Act: 0.4736. Min Act: -0.0000

Data Index: 1598098 (Python Code)

Max Activating Token Index: 156

Text #15

Max Range: 0.6274. Min Range: -0.6274

Max Act: 0.4715. Min Act: -0.0000

Data Index: 1490587 (Python Code)

Max Activating Token Index: 64

Text #16

Max Range: 0.6274. Min Range: -0.6274

Max Act: 0.4694. Min Act: -0.0000

Data Index: 1375984 (Python Code)

Max Activating Token Index: 517

Text #17

Max Range: 0.6274. Min Range: -0.6274

Max Act: 0.4841. Min Act: -0.0000

Data Index: 1451473 (Python Code)

Max Activating Token Index: 122

Text #18

Max Range: 0.6274. Min Range: -0.6274

Max Act: 0.4655. Min Act: -0.0001

Data Index: 1490912 (Python Code)

Max Activating Token Index: 271

Text #19

Max Range: 0.6274. Min Range: -0.6274

Max Act: 0.4958. Min Act: -0.0000

Data Index: 1544496 (Python Code)

Max Activating Token Index: 148