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

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

Neuron 707 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.5437. Min Act: -0.0000

Data Index: 1191273 (C4 (Web Text))

Max Activating Token Index: 233

Text #1

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.4556. Min Act: -0.0000

Data Index: 1010626 (C4 (Web Text))

Max Activating Token Index: 109

Text #2

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.4425. Min Act: -0.0000

Data Index: 850519 (C4 (Web Text))

Max Activating Token Index: 235

Text #3

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.4462. Min Act: -0.0000

Data Index: 945993 (C4 (Web Text))

Max Activating Token Index: 93

Text #4

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.4428. Min Act: -0.0000

Data Index: 34097 (C4 (Web Text))

Max Activating Token Index: 60

Text #5

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.3993. Min Act: -0.0000

Data Index: 634580 (C4 (Web Text))

Max Activating Token Index: 745

Text #6

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.4014. Min Act: -0.0000

Data Index: 1356664 (C4 (Web Text))

Max Activating Token Index: 97

Text #7

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.4129. Min Act: -0.0000

Data Index: 29796 (C4 (Web Text))

Max Activating Token Index: 558

Text #8

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.4021. Min Act: -0.0000

Data Index: 948187 (C4 (Web Text))

Max Activating Token Index: 330

Text #9

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.3932. Min Act: -0.0000

Data Index: 1296587 (C4 (Web Text))

Max Activating Token Index: 405

Text #10

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.3747. Min Act: -0.0000

Data Index: 647498 (C4 (Web Text))

Max Activating Token Index: 360

Text #11

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.3827. Min Act: -0.0000

Data Index: 39396 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.3943. Min Act: -0.0000

Data Index: 547131 (C4 (Web Text))

Max Activating Token Index: 1005

Text #13

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.3666. Min Act: -0.0000

Data Index: 957918 (C4 (Web Text))

Max Activating Token Index: 475

Text #14

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.3866. Min Act: -0.0000

Data Index: 221318 (C4 (Web Text))

Max Activating Token Index: 515

Text #15

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.3743. Min Act: -0.0000

Data Index: 1025178 (C4 (Web Text))

Max Activating Token Index: 401

Text #16

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.3751. Min Act: -0.0000

Data Index: 376511 (C4 (Web Text))

Max Activating Token Index: 503

Text #17

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.3718. Min Act: -0.0000

Data Index: 564513 (C4 (Web Text))

Max Activating Token Index: 312

Text #18

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.3758. Min Act: -0.0000

Data Index: 1183706 (C4 (Web Text))

Max Activating Token Index: 437

Text #19

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.3403. Min Act: -0.0000

Data Index: 893023 (C4 (Web Text))

Max Activating Token Index: 278