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

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

Neuron 3066 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.8330. Min Act: -0.0000

Data Index: 434409 (C4 (Web Text))

Max Activating Token Index: 506

Text #1

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.4284. Min Act: -0.0000

Data Index: 642795 (C4 (Web Text))

Max Activating Token Index: 488

Text #2

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.4041. Min Act: -0.0000

Data Index: 551249 (C4 (Web Text))

Max Activating Token Index: 855

Text #3

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.3047. Min Act: -0.0000

Data Index: 1535417 (Python Code)

Max Activating Token Index: 605

Text #4

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.3066. Min Act: -0.0000

Data Index: 486830 (C4 (Web Text))

Max Activating Token Index: 811

Text #5

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.3072. Min Act: -0.0000

Data Index: 1389763 (Python Code)

Max Activating Token Index: 684

Text #6

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.2933. Min Act: -0.0000

Data Index: 933625 (C4 (Web Text))

Max Activating Token Index: 150

Text #7

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.2721. Min Act: -0.0000

Data Index: 570430 (C4 (Web Text))

Max Activating Token Index: 297

Text #8

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.2565. Min Act: -0.0000

Data Index: 474757 (C4 (Web Text))

Max Activating Token Index: 362

Text #9

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.2558. Min Act: -0.0000

Data Index: 1073043 (C4 (Web Text))

Max Activating Token Index: 792

Text #10

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.2252. Min Act: -0.0000

Data Index: 724315 (C4 (Web Text))

Max Activating Token Index: 604

Text #11

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.2335. Min Act: -0.0000

Data Index: 652841 (C4 (Web Text))

Max Activating Token Index: 164

Text #12

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.2379. Min Act: -0.0000

Data Index: 617073 (C4 (Web Text))

Max Activating Token Index: 347

Text #13

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.2060. Min Act: -0.0000

Data Index: 339455 (C4 (Web Text))

Max Activating Token Index: 457

Text #14

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.2071. Min Act: -0.0000

Data Index: 526301 (C4 (Web Text))

Max Activating Token Index: 859

Text #15

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.1910. Min Act: -0.0000

Data Index: 1380514 (Python Code)

Max Activating Token Index: 665

Text #16

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.2008. Min Act: -0.0000

Data Index: 989699 (C4 (Web Text))

Max Activating Token Index: 235

Text #17

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.1578. Min Act: -0.0000

Data Index: 1181854 (C4 (Web Text))

Max Activating Token Index: 517

Text #18

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.1610. Min Act: -0.0000

Data Index: 1023793 (C4 (Web Text))

Max Activating Token Index: 189

Text #19

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.1591. Min Act: -0.0000

Data Index: 1103253 (C4 (Web Text))

Max Activating Token Index: 980