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

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

Neuron 1864 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5283. Min Range: -1.5283

Max Act: 1.5283. Min Act: -0.0000

Data Index: 1544746 (Python Code)

Max Activating Token Index: 490

Text #1

Max Range: 1.5283. Min Range: -1.5283

Max Act: 1.4548. Min Act: -0.0001

Data Index: 1655467 (Python Code)

Max Activating Token Index: 482

Text #2

Max Range: 1.5283. Min Range: -1.5283

Max Act: 1.3738. Min Act: 0.0002

Data Index: 1429168 (Python Code)

Max Activating Token Index: 586

Text #3

Max Range: 1.5283. Min Range: -1.5283

Max Act: 1.4451. Min Act: 0.0001

Data Index: 1588453 (Python Code)

Max Activating Token Index: 177

Text #4

Max Range: 1.5283. Min Range: -1.5283

Max Act: 1.3546. Min Act: -0.0000

Data Index: 1593242 (Python Code)

Max Activating Token Index: 643

Text #5

Max Range: 1.5283. Min Range: -1.5283

Max Act: 1.3875. Min Act: -0.0000

Data Index: 1385506 (Python Code)

Max Activating Token Index: 274

Text #6

Max Range: 1.5283. Min Range: -1.5283

Max Act: 1.3467. Min Act: 0.0001

Data Index: 1489935 (Python Code)

Max Activating Token Index: 650

Text #7

Max Range: 1.5283. Min Range: -1.5283

Max Act: 1.3389. Min Act: 0.0001

Data Index: 1644107 (Python Code)

Max Activating Token Index: 723

Text #8

Max Range: 1.5283. Min Range: -1.5283

Max Act: 1.3638. Min Act: -0.0001

Data Index: 1593124 (Python Code)

Max Activating Token Index: 83

Text #9

Max Range: 1.5283. Min Range: -1.5283

Max Act: 1.3187. Min Act: -0.0000

Data Index: 1626702 (Python Code)

Max Activating Token Index: 289

Text #10

Max Range: 1.5283. Min Range: -1.5283

Max Act: 1.3464. Min Act: -0.0000

Data Index: 1368069 (Python Code)

Max Activating Token Index: 162

Text #11

Max Range: 1.5283. Min Range: -1.5283

Max Act: 1.3773. Min Act: -0.0000

Data Index: 1362566 (Python Code)

Max Activating Token Index: 152

Text #12

Max Range: 1.5283. Min Range: -1.5283

Max Act: 1.2686. Min Act: -0.0000

Data Index: 1471644 (Python Code)

Max Activating Token Index: 289

Text #13

Max Range: 1.5283. Min Range: -1.5283

Max Act: 1.4170. Min Act: 0.0003

Data Index: 1396186 (Python Code)

Max Activating Token Index: 729

Text #14

Max Range: 1.5283. Min Range: -1.5283

Max Act: 1.3326. Min Act: -0.0000

Data Index: 1517246 (Python Code)

Max Activating Token Index: 289

Text #15

Max Range: 1.5283. Min Range: -1.5283

Max Act: 1.3752. Min Act: 0.0002

Data Index: 1577319 (Python Code)

Max Activating Token Index: 384

Text #16

Max Range: 1.5283. Min Range: -1.5283

Max Act: 1.3241. Min Act: 0.0002

Data Index: 1405547 (Python Code)

Max Activating Token Index: 433

Text #17

Max Range: 1.5283. Min Range: -1.5283

Max Act: 1.3277. Min Act: 0.0001

Data Index: 1558071 (Python Code)

Max Activating Token Index: 409

Text #18

Max Range: 1.5283. Min Range: -1.5283

Max Act: 1.3414. Min Act: 0.0001

Data Index: 1525960 (Python Code)

Max Activating Token Index: 695

Text #19

Max Range: 1.5283. Min Range: -1.5283

Max Act: 1.3258. Min Act: 0.0003

Data Index: 1379829 (Python Code)

Max Activating Token Index: 291