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

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

Neuron 2643 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0008. Min Act: -0.0001

Data Index: 1630655 (Python Code)

Max Activating Token Index: 334

Text #1

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0007. Min Act: -0.0001

Data Index: 1512600 (Python Code)

Max Activating Token Index: 573

Text #2

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0006. Min Act: -0.0002

Data Index: 14289 (C4 (Web Text))

Max Activating Token Index: 438

Text #3

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0006. Min Act: -0.0002

Data Index: 1428247 (Python Code)

Max Activating Token Index: 615

Text #4

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0006. Min Act: -0.0002

Data Index: 878319 (C4 (Web Text))

Max Activating Token Index: 684

Text #5

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0006. Min Act: -0.0001

Data Index: 1597726 (Python Code)

Max Activating Token Index: 598

Text #6

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0006. Min Act: -0.0002

Data Index: 1467043 (Python Code)

Max Activating Token Index: 516

Text #7

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0006. Min Act: -0.0002

Data Index: 779981 (C4 (Web Text))

Max Activating Token Index: 192

Text #8

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0006. Min Act: -0.0001

Data Index: 1554205 (Python Code)

Max Activating Token Index: 418

Text #9

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0005. Min Act: -0.0001

Data Index: 1529489 (Python Code)

Max Activating Token Index: 575

Text #10

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0005. Min Act: -0.0002

Data Index: 355803 (C4 (Web Text))

Max Activating Token Index: 691

Text #11

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0005. Min Act: -0.0001

Data Index: 295086 (C4 (Web Text))

Max Activating Token Index: 521

Text #12

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0005. Min Act: -0.0002

Data Index: 1320283 (C4 (Web Text))

Max Activating Token Index: 492

Text #13

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0005. Min Act: -0.0002

Data Index: 1551646 (Python Code)

Max Activating Token Index: 562

Text #14

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0005. Min Act: -0.0002

Data Index: 1637038 (Python Code)

Max Activating Token Index: 485

Text #15

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0005. Min Act: -0.0001

Data Index: 1452653 (Python Code)

Max Activating Token Index: 695

Text #16

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0005. Min Act: -0.0002

Data Index: 1648288 (Python Code)

Max Activating Token Index: 586

Text #17

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0005. Min Act: -0.0001

Data Index: 241232 (C4 (Web Text))

Max Activating Token Index: 596

Text #18

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0005. Min Act: -0.0002

Data Index: 648836 (C4 (Web Text))

Max Activating Token Index: 312

Text #19

Max Range: 0.0008. Min Range: -0.0008

Max Act: 0.0005. Min Act: -0.0002

Data Index: 1585200 (Python Code)

Max Activating Token Index: 318