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

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

Neuron 3590 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5699. Min Range: -1.5699

Max Act: 1.5699. Min Act: -0.0000

Data Index: 316600 (C4 (Web Text))

Max Activating Token Index: 478

Text #1

Max Range: 1.5699. Min Range: -1.5699

Max Act: 1.2981. Min Act: -0.0000

Data Index: 1365530 (Python Code)

Max Activating Token Index: 954

Text #2

Max Range: 1.5699. Min Range: -1.5699

Max Act: 1.1723. Min Act: -0.0000

Data Index: 171872 (C4 (Web Text))

Max Activating Token Index: 97

Text #3

Max Range: 1.5699. Min Range: -1.5699

Max Act: 1.0694. Min Act: -0.0000

Data Index: 747025 (C4 (Web Text))

Max Activating Token Index: 748

Text #4

Max Range: 1.5699. Min Range: -1.5699

Max Act: 0.9857. Min Act: -0.0000

Data Index: 990147 (C4 (Web Text))

Max Activating Token Index: 170

Text #5

Max Range: 1.5699. Min Range: -1.5699

Max Act: 0.9632. Min Act: -0.0000

Data Index: 818511 (C4 (Web Text))

Max Activating Token Index: 104

Text #6

Max Range: 1.5699. Min Range: -1.5699

Max Act: 1.0453. Min Act: -0.0000

Data Index: 1605682 (Python Code)

Max Activating Token Index: 349

Text #7

Max Range: 1.5699. Min Range: -1.5699

Max Act: 0.9990. Min Act: -0.0000

Data Index: 1255735 (C4 (Web Text))

Max Activating Token Index: 466

Text #8

Max Range: 1.5699. Min Range: -1.5699

Max Act: 0.9905. Min Act: -0.0000

Data Index: 441274 (C4 (Web Text))

Max Activating Token Index: 770

Text #9

Max Range: 1.5699. Min Range: -1.5699

Max Act: 1.0864. Min Act: -0.0000

Data Index: 1451813 (Python Code)

Max Activating Token Index: 586

Text #10

Max Range: 1.5699. Min Range: -1.5699

Max Act: 0.8883. Min Act: -0.0000

Data Index: 348622 (C4 (Web Text))

Max Activating Token Index: 83

Text #11

Max Range: 1.5699. Min Range: -1.5699

Max Act: 0.9671. Min Act: -0.0000

Data Index: 691892 (C4 (Web Text))

Max Activating Token Index: 466

Text #12

Max Range: 1.5699. Min Range: -1.5699

Max Act: 0.8162. Min Act: 0.0000

Data Index: 894488 (C4 (Web Text))

Max Activating Token Index: 759

Text #13

Max Range: 1.5699. Min Range: -1.5699

Max Act: 0.8899. Min Act: -0.0000

Data Index: 49247 (C4 (Web Text))

Max Activating Token Index: 255

Text #14

Max Range: 1.5699. Min Range: -1.5699

Max Act: 0.8862. Min Act: -0.0000

Data Index: 1567386 (Python Code)

Max Activating Token Index: 183

Text #15

Max Range: 1.5699. Min Range: -1.5699

Max Act: 0.9525. Min Act: -0.0000

Data Index: 810854 (C4 (Web Text))

Max Activating Token Index: 787

Text #16

Max Range: 1.5699. Min Range: -1.5699

Max Act: 0.8402. Min Act: -0.0000

Data Index: 439328 (C4 (Web Text))

Max Activating Token Index: 129

Text #17

Max Range: 1.5699. Min Range: -1.5699

Max Act: 0.9462. Min Act: -0.0000

Data Index: 201909 (C4 (Web Text))

Max Activating Token Index: 158

Text #18

Max Range: 1.5699. Min Range: -1.5699

Max Act: 0.8520. Min Act: -0.0000

Data Index: 557476 (C4 (Web Text))

Max Activating Token Index: 364

Text #19

Max Range: 1.5699. Min Range: -1.5699

Max Act: 0.8334. Min Act: -0.0000

Data Index: 1465451 (Python Code)

Max Activating Token Index: 743