Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1884 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0899. Min Act: -0.0001

Data Index: 1477493 (Python Code)

Max Activating Token Index: 224

Text #1

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0904. Min Act: -0.0001

Data Index: 1401503 (Python Code)

Max Activating Token Index: 167

Text #2

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0809. Min Act: -0.0001

Data Index: 1384204 (Python Code)

Max Activating Token Index: 664

Text #3

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0843. Min Act: -0.0001

Data Index: 1518231 (Python Code)

Max Activating Token Index: 178

Text #4

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0804. Min Act: -0.0001

Data Index: 656343 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0794. Min Act: -0.0001

Data Index: 1569641 (Python Code)

Max Activating Token Index: 407

Text #6

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0775. Min Act: -0.0001

Data Index: 1425360 (Python Code)

Max Activating Token Index: 385

Text #7

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0733. Min Act: -0.0001

Data Index: 1554182 (Python Code)

Max Activating Token Index: 394

Text #8

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0742. Min Act: -0.0001

Data Index: 1572158 (Python Code)

Max Activating Token Index: 316

Text #9

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0732. Min Act: -0.0001

Data Index: 1531934 (Python Code)

Max Activating Token Index: 475

Text #10

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0758. Min Act: -0.0001

Data Index: 1569681 (Python Code)

Max Activating Token Index: 594

Text #11

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0765. Min Act: -0.0001

Data Index: 1502680 (Python Code)

Max Activating Token Index: 382

Text #12

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0716. Min Act: -0.0001

Data Index: 1581774 (Python Code)

Max Activating Token Index: 128

Text #13

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0676. Min Act: -0.0001

Data Index: 1495615 (Python Code)

Max Activating Token Index: 344

Text #14

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0748. Min Act: -0.0001

Data Index: 1377475 (Python Code)

Max Activating Token Index: 734

Text #15

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0717. Min Act: -0.0001

Data Index: 1459361 (Python Code)

Max Activating Token Index: 394

Text #16

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0687. Min Act: -0.0001

Data Index: 1511119 (Python Code)

Max Activating Token Index: 422

Text #17

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0680. Min Act: -0.0001

Data Index: 1540335 (Python Code)

Max Activating Token Index: 262

Text #18

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0693. Min Act: -0.0001

Data Index: 1623883 (Python Code)

Max Activating Token Index: 413

Text #19

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0647. Min Act: -0.0001

Data Index: 1408440 (Python Code)

Max Activating Token Index: 946