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

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

Neuron 1374 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0599. Min Range: -2.0599

Max Act: 2.0599. Min Act: -0.0000

Data Index: 1535720 (Python Code)

Max Activating Token Index: 319

Text #1

Max Range: 2.0599. Min Range: -2.0599

Max Act: 1.8673. Min Act: -0.0000

Data Index: 1578499 (Python Code)

Max Activating Token Index: 661

Text #2

Max Range: 2.0599. Min Range: -2.0599

Max Act: 1.9325. Min Act: -0.0000

Data Index: 1573289 (Python Code)

Max Activating Token Index: 816

Text #3

Max Range: 2.0599. Min Range: -2.0599

Max Act: 2.0010. Min Act: -0.0000

Data Index: 1517084 (Python Code)

Max Activating Token Index: 914

Text #4

Max Range: 2.0599. Min Range: -2.0599

Max Act: 1.9063. Min Act: -0.0000

Data Index: 1430959 (Python Code)

Max Activating Token Index: 852

Text #5

Max Range: 2.0599. Min Range: -2.0599

Max Act: 1.9505. Min Act: -0.0000

Data Index: 1380765 (Python Code)

Max Activating Token Index: 590

Text #6

Max Range: 2.0599. Min Range: -2.0599

Max Act: 1.7824. Min Act: -0.0000

Data Index: 1498477 (Python Code)

Max Activating Token Index: 983

Text #7

Max Range: 2.0599. Min Range: -2.0599

Max Act: 1.8712. Min Act: -0.0000

Data Index: 1403244 (Python Code)

Max Activating Token Index: 370

Text #8

Max Range: 2.0599. Min Range: -2.0599

Max Act: 1.6679. Min Act: -0.0000

Data Index: 1441416 (Python Code)

Max Activating Token Index: 279

Text #9

Max Range: 2.0599. Min Range: -2.0599

Max Act: 1.8099. Min Act: -0.0000

Data Index: 1655846 (Python Code)

Max Activating Token Index: 667

Text #10

Max Range: 2.0599. Min Range: -2.0599

Max Act: 1.8519. Min Act: -0.0000

Data Index: 1654922 (Python Code)

Max Activating Token Index: 683

Text #11

Max Range: 2.0599. Min Range: -2.0599

Max Act: 1.7882. Min Act: -0.0000

Data Index: 1441076 (Python Code)

Max Activating Token Index: 811

Text #12

Max Range: 2.0599. Min Range: -2.0599

Max Act: 1.7815. Min Act: -0.0000

Data Index: 1372473 (Python Code)

Max Activating Token Index: 617

Text #13

Max Range: 2.0599. Min Range: -2.0599

Max Act: 1.7994. Min Act: -0.0000

Data Index: 1576966 (Python Code)

Max Activating Token Index: 521

Text #14

Max Range: 2.0599. Min Range: -2.0599

Max Act: 1.8386. Min Act: -0.0000

Data Index: 1479513 (Python Code)

Max Activating Token Index: 214

Text #15

Max Range: 2.0599. Min Range: -2.0599

Max Act: 1.7558. Min Act: -0.0000

Data Index: 1375090 (Python Code)

Max Activating Token Index: 1019

Text #16

Max Range: 2.0599. Min Range: -2.0599

Max Act: 1.7307. Min Act: -0.0000

Data Index: 1449111 (Python Code)

Max Activating Token Index: 668

Text #17

Max Range: 2.0599. Min Range: -2.0599

Max Act: 1.6567. Min Act: -0.0000

Data Index: 1594356 (Python Code)

Max Activating Token Index: 638

Text #18

Max Range: 2.0599. Min Range: -2.0599

Max Act: 1.7077. Min Act: -0.0000

Data Index: 1508136 (Python Code)

Max Activating Token Index: 520

Text #19

Max Range: 2.0599. Min Range: -2.0599

Max Act: 1.7933. Min Act: -0.0001

Data Index: 1515833 (Python Code)

Max Activating Token Index: 766