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

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

Neuron 304 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5948. Min Range: -1.5948

Max Act: 1.5948. Min Act: -0.0000

Data Index: 360217 (C4 (Web Text))

Max Activating Token Index: 901

Text #1

Max Range: 1.5948. Min Range: -1.5948

Max Act: 1.4492. Min Act: -0.0000

Data Index: 122453 (C4 (Web Text))

Max Activating Token Index: 690

Text #2

Max Range: 1.5948. Min Range: -1.5948

Max Act: 1.3648. Min Act: -0.0000

Data Index: 766255 (C4 (Web Text))

Max Activating Token Index: 559

Text #3

Max Range: 1.5948. Min Range: -1.5948

Max Act: 1.2764. Min Act: -0.0000

Data Index: 1243865 (C4 (Web Text))

Max Activating Token Index: 603

Text #4

Max Range: 1.5948. Min Range: -1.5948

Max Act: 1.2243. Min Act: -0.0000

Data Index: 849681 (C4 (Web Text))

Max Activating Token Index: 1002

Text #5

Max Range: 1.5948. Min Range: -1.5948

Max Act: 1.1816. Min Act: -0.0000

Data Index: 50940 (C4 (Web Text))

Max Activating Token Index: 950

Text #6

Max Range: 1.5948. Min Range: -1.5948

Max Act: 1.1374. Min Act: -0.0000

Data Index: 408585 (C4 (Web Text))

Max Activating Token Index: 831

Text #7

Max Range: 1.5948. Min Range: -1.5948

Max Act: 1.2869. Min Act: -0.0000

Data Index: 204507 (C4 (Web Text))

Max Activating Token Index: 368

Text #8

Max Range: 1.5948. Min Range: -1.5948

Max Act: 1.0992. Min Act: -0.0000

Data Index: 770272 (C4 (Web Text))

Max Activating Token Index: 506

Text #9

Max Range: 1.5948. Min Range: -1.5948

Max Act: 1.0960. Min Act: -0.0000

Data Index: 1324128 (C4 (Web Text))

Max Activating Token Index: 45

Text #10

Max Range: 1.5948. Min Range: -1.5948

Max Act: 1.0990. Min Act: -0.0000

Data Index: 1277638 (C4 (Web Text))

Max Activating Token Index: 139

Text #11

Max Range: 1.5948. Min Range: -1.5948

Max Act: 1.0789. Min Act: -0.0000

Data Index: 216769 (C4 (Web Text))

Max Activating Token Index: 393

Text #12

Max Range: 1.5948. Min Range: -1.5948

Max Act: 1.0923. Min Act: -0.0000

Data Index: 1358941 (C4 (Web Text))

Max Activating Token Index: 238

Text #13

Max Range: 1.5948. Min Range: -1.5948

Max Act: 1.0812. Min Act: -0.0000

Data Index: 894608 (C4 (Web Text))

Max Activating Token Index: 587

Text #14

Max Range: 1.5948. Min Range: -1.5948

Max Act: 1.0837. Min Act: -0.0000

Data Index: 206828 (C4 (Web Text))

Max Activating Token Index: 956

Text #15

Max Range: 1.5948. Min Range: -1.5948

Max Act: 1.1403. Min Act: -0.0000

Data Index: 942218 (C4 (Web Text))

Max Activating Token Index: 481

Text #16

Max Range: 1.5948. Min Range: -1.5948

Max Act: 1.1250. Min Act: -0.0000

Data Index: 684377 (C4 (Web Text))

Max Activating Token Index: 575

Text #17

Max Range: 1.5948. Min Range: -1.5948

Max Act: 0.9759. Min Act: -0.0000

Data Index: 214281 (C4 (Web Text))

Max Activating Token Index: 135

Text #18

Max Range: 1.5948. Min Range: -1.5948

Max Act: 1.0395. Min Act: -0.0000

Data Index: 560477 (C4 (Web Text))

Max Activating Token Index: 876

Text #19

Max Range: 1.5948. Min Range: -1.5948

Max Act: 0.9582. Min Act: -0.0000

Data Index: 78282 (C4 (Web Text))

Max Activating Token Index: 777