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

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

Neuron 5934 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.6463. Min Act: -0.0000

Data Index: 967229 (C4 (Web Text))

Max Activating Token Index: 346

Text #1

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.6655. Min Act: -0.0000

Data Index: 452385 (C4 (Web Text))

Max Activating Token Index: 355

Text #2

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.5607. Min Act: -0.0000

Data Index: 92347 (C4 (Web Text))

Max Activating Token Index: 921

Text #3

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.5627. Min Act: -0.0000

Data Index: 1345176 (C4 (Web Text))

Max Activating Token Index: 408

Text #4

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.5291. Min Act: -0.0000

Data Index: 474393 (C4 (Web Text))

Max Activating Token Index: 539

Text #5

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.5174. Min Act: -0.0000

Data Index: 1008033 (C4 (Web Text))

Max Activating Token Index: 909

Text #6

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.5237. Min Act: -0.0000

Data Index: 665025 (C4 (Web Text))

Max Activating Token Index: 300

Text #7

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.5716. Min Act: -0.0000

Data Index: 543288 (C4 (Web Text))

Max Activating Token Index: 959

Text #8

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.5600. Min Act: -0.0000

Data Index: 746298 (C4 (Web Text))

Max Activating Token Index: 947

Text #9

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.4986. Min Act: -0.0000

Data Index: 960571 (C4 (Web Text))

Max Activating Token Index: 832

Text #10

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.4975. Min Act: -0.0000

Data Index: 189526 (C4 (Web Text))

Max Activating Token Index: 320

Text #11

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.5473. Min Act: -0.0000

Data Index: 282397 (C4 (Web Text))

Max Activating Token Index: 755

Text #12

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.4823. Min Act: -0.0000

Data Index: 1433751 (Python Code)

Max Activating Token Index: 1001

Text #13

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.4992. Min Act: -0.0000

Data Index: 295617 (C4 (Web Text))

Max Activating Token Index: 755

Text #14

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.4671. Min Act: -0.0000

Data Index: 1478980 (Python Code)

Max Activating Token Index: 792

Text #15

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.5005. Min Act: -0.0000

Data Index: 347672 (C4 (Web Text))

Max Activating Token Index: 384

Text #16

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.5294. Min Act: -0.0000

Data Index: 914236 (C4 (Web Text))

Max Activating Token Index: 262

Text #17

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.5305. Min Act: -0.0000

Data Index: 1346978 (C4 (Web Text))

Max Activating Token Index: 368

Text #18

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.4630. Min Act: -0.0000

Data Index: 1402255 (Python Code)

Max Activating Token Index: 509

Text #19

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.4919. Min Act: -0.0000

Data Index: 1627886 (Python Code)

Max Activating Token Index: 394