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

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

Neuron 2041 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4989. Min Range: -4.4989

Max Act: 4.4989. Min Act: -0.0000

Data Index: 1639522 (Python Code)

Max Activating Token Index: 640

Text #1

Max Range: 4.4989. Min Range: -4.4989

Max Act: 3.6219. Min Act: -0.0000

Data Index: 773063 (C4 (Web Text))

Max Activating Token Index: 553

Text #2

Max Range: 4.4989. Min Range: -4.4989

Max Act: 3.8012. Min Act: -0.0000

Data Index: 1023907 (C4 (Web Text))

Max Activating Token Index: 564

Text #3

Max Range: 4.4989. Min Range: -4.4989

Max Act: 3.6291. Min Act: -0.0000

Data Index: 770988 (C4 (Web Text))

Max Activating Token Index: 743

Text #4

Max Range: 4.4989. Min Range: -4.4989

Max Act: 3.4396. Min Act: -0.0000

Data Index: 2216 (C4 (Web Text))

Max Activating Token Index: 340

Text #5

Max Range: 4.4989. Min Range: -4.4989

Max Act: 3.0998. Min Act: -0.0000

Data Index: 1604252 (Python Code)

Max Activating Token Index: 941

Text #6

Max Range: 4.4989. Min Range: -4.4989

Max Act: 3.2134. Min Act: -0.0000

Data Index: 1535958 (Python Code)

Max Activating Token Index: 231

Text #7

Max Range: 4.4989. Min Range: -4.4989

Max Act: 2.8794. Min Act: -0.0000

Data Index: 666045 (C4 (Web Text))

Max Activating Token Index: 421

Text #8

Max Range: 4.4989. Min Range: -4.4989

Max Act: 2.8419. Min Act: -0.0000

Data Index: 1369693 (Python Code)

Max Activating Token Index: 357

Text #9

Max Range: 4.4989. Min Range: -4.4989

Max Act: 2.8605. Min Act: -0.0000

Data Index: 1498492 (Python Code)

Max Activating Token Index: 631

Text #10

Max Range: 4.4989. Min Range: -4.4989

Max Act: 2.7995. Min Act: -0.0000

Data Index: 1368311 (Python Code)

Max Activating Token Index: 791

Text #11

Max Range: 4.4989. Min Range: -4.4989

Max Act: 2.5892. Min Act: -0.0000

Data Index: 1494561 (Python Code)

Max Activating Token Index: 786

Text #12

Max Range: 4.4989. Min Range: -4.4989

Max Act: 2.8681. Min Act: -0.0000

Data Index: 1542742 (Python Code)

Max Activating Token Index: 606

Text #13

Max Range: 4.4989. Min Range: -4.4989

Max Act: 2.7201. Min Act: -0.0000

Data Index: 260603 (C4 (Web Text))

Max Activating Token Index: 470

Text #14

Max Range: 4.4989. Min Range: -4.4989

Max Act: 2.8272. Min Act: -0.0000

Data Index: 1557388 (Python Code)

Max Activating Token Index: 900

Text #15

Max Range: 4.4989. Min Range: -4.4989

Max Act: 2.8209. Min Act: -0.0000

Data Index: 1652078 (Python Code)

Max Activating Token Index: 679

Text #16

Max Range: 4.4989. Min Range: -4.4989

Max Act: 2.8238. Min Act: -0.0000

Data Index: 604867 (C4 (Web Text))

Max Activating Token Index: 608

Text #17

Max Range: 4.4989. Min Range: -4.4989

Max Act: 2.6490. Min Act: -0.0000

Data Index: 1377218 (Python Code)

Max Activating Token Index: 795

Text #18

Max Range: 4.4989. Min Range: -4.4989

Max Act: 2.6646. Min Act: -0.0000

Data Index: 1417278 (Python Code)

Max Activating Token Index: 108

Text #19

Max Range: 4.4989. Min Range: -4.4989

Max Act: 2.8855. Min Act: -0.0000

Data Index: 1392017 (Python Code)

Max Activating Token Index: 827