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

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

Neuron 1036 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0884. Min Act: -0.0002

Data Index: 384535 (C4 (Web Text))

Max Activating Token Index: 955

Text #1

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0754. Min Act: -0.0002

Data Index: 1393231 (Python Code)

Max Activating Token Index: 259

Text #2

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0596. Min Act: -0.0002

Data Index: 1564090 (Python Code)

Max Activating Token Index: 1002

Text #3

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0579. Min Act: -0.0002

Data Index: 1454949 (Python Code)

Max Activating Token Index: 388

Text #4

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0632. Min Act: -0.0002

Data Index: 878219 (C4 (Web Text))

Max Activating Token Index: 724

Text #5

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0499. Min Act: -0.0002

Data Index: 847215 (C4 (Web Text))

Max Activating Token Index: 689

Text #6

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0514. Min Act: -0.0002

Data Index: 1393759 (Python Code)

Max Activating Token Index: 1004

Text #7

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0502. Min Act: -0.0002

Data Index: 1404429 (Python Code)

Max Activating Token Index: 1005

Text #8

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0477. Min Act: -0.0002

Data Index: 1437428 (Python Code)

Max Activating Token Index: 520

Text #9

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0372. Min Act: -0.0002

Data Index: 1387539 (Python Code)

Max Activating Token Index: 222

Text #10

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0347. Min Act: -0.0002

Data Index: 1523484 (Python Code)

Max Activating Token Index: 506

Text #11

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0318. Min Act: -0.0002

Data Index: 1589428 (Python Code)

Max Activating Token Index: 756

Text #12

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0346. Min Act: -0.0002

Data Index: 1469380 (Python Code)

Max Activating Token Index: 284

Text #13

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0323. Min Act: -0.0002

Data Index: 1632928 (Python Code)

Max Activating Token Index: 496

Text #14

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0317. Min Act: -0.0002

Data Index: 1532445 (Python Code)

Max Activating Token Index: 267

Text #15

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0325. Min Act: -0.0002

Data Index: 1376931 (Python Code)

Max Activating Token Index: 758

Text #16

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0303. Min Act: -0.0002

Data Index: 1526982 (Python Code)

Max Activating Token Index: 240

Text #17

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0314. Min Act: -0.0002

Data Index: 1618831 (Python Code)

Max Activating Token Index: 495

Text #18

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0329. Min Act: -0.0002

Data Index: 1560400 (Python Code)

Max Activating Token Index: 12

Text #19

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0288. Min Act: -0.0002

Data Index: 1609229 (Python Code)

Max Activating Token Index: 672