Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1377 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.7240. Min Act: -0.0000

Data Index: 1480558 (Python Code)

Max Activating Token Index: 881

Text #1

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.2758. Min Act: -0.0000

Data Index: 1518286 (Python Code)

Max Activating Token Index: 832

Text #2

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.2065. Min Act: -0.0000

Data Index: 1371199 (Python Code)

Max Activating Token Index: 137

Text #3

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.1217. Min Act: -0.0000

Data Index: 1531883 (Python Code)

Max Activating Token Index: 583

Text #4

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.1662. Min Act: -0.0000

Data Index: 1634705 (Python Code)

Max Activating Token Index: 432

Text #5

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.1433. Min Act: -0.0000

Data Index: 1394386 (Python Code)

Max Activating Token Index: 12

Text #6

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.1217. Min Act: -0.0000

Data Index: 1375049 (Python Code)

Max Activating Token Index: 653

Text #7

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.1021. Min Act: 0.0000

Data Index: 1366380 (Python Code)

Max Activating Token Index: 30

Text #8

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.0990. Min Act: -0.0000

Data Index: 766727 (C4 (Web Text))

Max Activating Token Index: 408

Text #9

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.0921. Min Act: -0.0000

Data Index: 1511544 (Python Code)

Max Activating Token Index: 807

Text #10

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.0907. Min Act: -0.0000

Data Index: 1654306 (Python Code)

Max Activating Token Index: 308

Text #11

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.1000. Min Act: -0.0000

Data Index: 1477240 (Python Code)

Max Activating Token Index: 385

Text #12

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.0761. Min Act: -0.0000

Data Index: 1584643 (Python Code)

Max Activating Token Index: 144

Text #13

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.0726. Min Act: -0.0000

Data Index: 1453699 (Python Code)

Max Activating Token Index: 740

Text #14

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.1357. Min Act: -0.0000

Data Index: 1441439 (Python Code)

Max Activating Token Index: 454

Text #15

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.0507. Min Act: 0.0000

Data Index: 365261 (C4 (Web Text))

Max Activating Token Index: 757

Text #16

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.1075. Min Act: -0.0000

Data Index: 502300 (C4 (Web Text))

Max Activating Token Index: 309

Text #17

Max Range: 1.7240. Min Range: -1.7240

Max Act: 0.9417. Min Act: -0.0000

Data Index: 1472382 (Python Code)

Max Activating Token Index: 888

Text #18

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.0029. Min Act: -0.0000

Data Index: 961586 (C4 (Web Text))

Max Activating Token Index: 306

Text #19

Max Range: 1.7240. Min Range: -1.7240

Max Act: 0.9978. Min Act: -0.0000

Data Index: 1393998 (Python Code)

Max Activating Token Index: 900