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

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

Neuron 588 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.8798. Min Act: -0.0000

Data Index: 1437502 (Python Code)

Max Activating Token Index: 591

Text #1

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.6866. Min Act: -0.0000

Data Index: 1546417 (Python Code)

Max Activating Token Index: 323

Text #2

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.7352. Min Act: -0.0000

Data Index: 1644177 (Python Code)

Max Activating Token Index: 773

Text #3

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.5945. Min Act: -0.0000

Data Index: 1596046 (Python Code)

Max Activating Token Index: 639

Text #4

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.6264. Min Act: -0.0000

Data Index: 1439662 (Python Code)

Max Activating Token Index: 595

Text #5

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.5612. Min Act: -0.0000

Data Index: 1512331 (Python Code)

Max Activating Token Index: 218

Text #6

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.5707. Min Act: -0.0000

Data Index: 1593318 (Python Code)

Max Activating Token Index: 147

Text #7

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.5427. Min Act: -0.0000

Data Index: 1418755 (Python Code)

Max Activating Token Index: 108

Text #8

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.6076. Min Act: -0.0000

Data Index: 1569952 (Python Code)

Max Activating Token Index: 564

Text #9

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.5594. Min Act: -0.0000

Data Index: 1593205 (Python Code)

Max Activating Token Index: 774

Text #10

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.5341. Min Act: -0.0000

Data Index: 1396746 (Python Code)

Max Activating Token Index: 48

Text #11

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.5239. Min Act: -0.0000

Data Index: 1549591 (Python Code)

Max Activating Token Index: 557

Text #12

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.4998. Min Act: -0.0000

Data Index: 1638199 (Python Code)

Max Activating Token Index: 227

Text #13

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.5023. Min Act: -0.0000

Data Index: 1604820 (Python Code)

Max Activating Token Index: 106

Text #14

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.4831. Min Act: -0.0000

Data Index: 1626490 (Python Code)

Max Activating Token Index: 781

Text #15

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.5106. Min Act: -0.0000

Data Index: 1612239 (Python Code)

Max Activating Token Index: 674

Text #16

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.4598. Min Act: 0.0000

Data Index: 1090566 (C4 (Web Text))

Max Activating Token Index: 33

Text #17

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.4402. Min Act: -0.0000

Data Index: 1555214 (Python Code)

Max Activating Token Index: 382

Text #18

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.4370. Min Act: -0.0000

Data Index: 1443611 (Python Code)

Max Activating Token Index: 774

Text #19

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.4433. Min Act: -0.0000

Data Index: 1463820 (Python Code)

Max Activating Token Index: 753