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

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

Neuron 4688 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6506. Min Range: -0.6506

Max Act: 0.6506. Min Act: -0.0000

Data Index: 32495 (C4 (Web Text))

Max Activating Token Index: 700

Text #1

Max Range: 0.6506. Min Range: -0.6506

Max Act: 0.5649. Min Act: -0.0000

Data Index: 634643 (C4 (Web Text))

Max Activating Token Index: 569

Text #2

Max Range: 0.6506. Min Range: -0.6506

Max Act: 0.5656. Min Act: -0.0000

Data Index: 636119 (C4 (Web Text))

Max Activating Token Index: 232

Text #3

Max Range: 0.6506. Min Range: -0.6506

Max Act: 0.4744. Min Act: 0.0000

Data Index: 1201019 (C4 (Web Text))

Max Activating Token Index: 174

Text #4

Max Range: 0.6506. Min Range: -0.6506

Max Act: 0.4690. Min Act: -0.0000

Data Index: 975392 (C4 (Web Text))

Max Activating Token Index: 464

Text #5

Max Range: 0.6506. Min Range: -0.6506

Max Act: 0.4854. Min Act: -0.0000

Data Index: 406453 (C4 (Web Text))

Max Activating Token Index: 456

Text #6

Max Range: 0.6506. Min Range: -0.6506

Max Act: 0.4838. Min Act: -0.0000

Data Index: 68678 (C4 (Web Text))

Max Activating Token Index: 645

Text #7

Max Range: 0.6506. Min Range: -0.6506

Max Act: 0.5235. Min Act: 0.0000

Data Index: 42380 (C4 (Web Text))

Max Activating Token Index: 432

Text #8

Max Range: 0.6506. Min Range: -0.6506

Max Act: 0.4636. Min Act: -0.0000

Data Index: 1329369 (C4 (Web Text))

Max Activating Token Index: 430

Text #9

Max Range: 0.6506. Min Range: -0.6506

Max Act: 0.4376. Min Act: -0.0000

Data Index: 105181 (C4 (Web Text))

Max Activating Token Index: 376

Text #10

Max Range: 0.6506. Min Range: -0.6506

Max Act: 0.4451. Min Act: -0.0000

Data Index: 1115160 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 0.6506. Min Range: -0.6506

Max Act: 0.4207. Min Act: -0.0000

Data Index: 671217 (C4 (Web Text))

Max Activating Token Index: 255

Text #12

Max Range: 0.6506. Min Range: -0.6506

Max Act: 0.3782. Min Act: -0.0000

Data Index: 1516125 (Python Code)

Max Activating Token Index: 963

Text #13

Max Range: 0.6506. Min Range: -0.6506

Max Act: 0.3991. Min Act: -0.0000

Data Index: 1404513 (Python Code)

Max Activating Token Index: 63

Text #14

Max Range: 0.6506. Min Range: -0.6506

Max Act: 0.4106. Min Act: -0.0000

Data Index: 433426 (C4 (Web Text))

Max Activating Token Index: 239

Text #15

Max Range: 0.6506. Min Range: -0.6506

Max Act: 0.4272. Min Act: -0.0000

Data Index: 1581284 (Python Code)

Max Activating Token Index: 796

Text #16

Max Range: 0.6506. Min Range: -0.6506

Max Act: 0.3872. Min Act: -0.0000

Data Index: 1507606 (Python Code)

Max Activating Token Index: 154

Text #17

Max Range: 0.6506. Min Range: -0.6506

Max Act: 0.3694. Min Act: -0.0000

Data Index: 896763 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 0.6506. Min Range: -0.6506

Max Act: 0.3846. Min Act: -0.0000

Data Index: 1551315 (Python Code)

Max Activating Token Index: 130

Text #19

Max Range: 0.6506. Min Range: -0.6506

Max Act: 0.4130. Min Act: -0.0000

Data Index: 1380365 (Python Code)

Max Activating Token Index: 848