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

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

Neuron 4370 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8147. Min Range: -3.8147

Max Act: 3.8147. Min Act: -0.0000

Data Index: 1655283 (Python Code)

Max Activating Token Index: 601

Text #1

Max Range: 3.8147. Min Range: -3.8147

Max Act: 3.4272. Min Act: -0.0000

Data Index: 1523166 (Python Code)

Max Activating Token Index: 134

Text #2

Max Range: 3.8147. Min Range: -3.8147

Max Act: 2.9885. Min Act: -0.0000

Data Index: 1586845 (Python Code)

Max Activating Token Index: 843

Text #3

Max Range: 3.8147. Min Range: -3.8147

Max Act: 2.9844. Min Act: -0.0000

Data Index: 1572544 (Python Code)

Max Activating Token Index: 753

Text #4

Max Range: 3.8147. Min Range: -3.8147

Max Act: 3.1791. Min Act: -0.0000

Data Index: 1218864 (C4 (Web Text))

Max Activating Token Index: 304

Text #5

Max Range: 3.8147. Min Range: -3.8147

Max Act: 2.9883. Min Act: -0.0000

Data Index: 1461787 (Python Code)

Max Activating Token Index: 495

Text #6

Max Range: 3.8147. Min Range: -3.8147

Max Act: 2.8542. Min Act: -0.0000

Data Index: 195009 (C4 (Web Text))

Max Activating Token Index: 562

Text #7

Max Range: 3.8147. Min Range: -3.8147

Max Act: 2.8356. Min Act: -0.0000

Data Index: 1441589 (Python Code)

Max Activating Token Index: 771

Text #8

Max Range: 3.8147. Min Range: -3.8147

Max Act: 2.6829. Min Act: -0.0000

Data Index: 1640614 (Python Code)

Max Activating Token Index: 679

Text #9

Max Range: 3.8147. Min Range: -3.8147

Max Act: 2.7948. Min Act: -0.0000

Data Index: 1383900 (Python Code)

Max Activating Token Index: 820

Text #10

Max Range: 3.8147. Min Range: -3.8147

Max Act: 2.5769. Min Act: -0.0000

Data Index: 1436110 (Python Code)

Max Activating Token Index: 302

Text #11

Max Range: 3.8147. Min Range: -3.8147

Max Act: 2.8104. Min Act: -0.0000

Data Index: 1563650 (Python Code)

Max Activating Token Index: 874

Text #12

Max Range: 3.8147. Min Range: -3.8147

Max Act: 2.9177. Min Act: -0.0000

Data Index: 1566665 (Python Code)

Max Activating Token Index: 591

Text #13

Max Range: 3.8147. Min Range: -3.8147

Max Act: 2.5027. Min Act: -0.0000

Data Index: 1490640 (Python Code)

Max Activating Token Index: 812

Text #14

Max Range: 3.8147. Min Range: -3.8147

Max Act: 2.5991. Min Act: -0.0000

Data Index: 1431667 (Python Code)

Max Activating Token Index: 580

Text #15

Max Range: 3.8147. Min Range: -3.8147

Max Act: 2.4465. Min Act: -0.0000

Data Index: 1568954 (Python Code)

Max Activating Token Index: 571

Text #16

Max Range: 3.8147. Min Range: -3.8147

Max Act: 2.5170. Min Act: -0.0000

Data Index: 1566189 (Python Code)

Max Activating Token Index: 23

Text #17

Max Range: 3.8147. Min Range: -3.8147

Max Act: 2.3841. Min Act: -0.0000

Data Index: 1076810 (C4 (Web Text))

Max Activating Token Index: 671

Text #18

Max Range: 3.8147. Min Range: -3.8147

Max Act: 2.5962. Min Act: -0.0000

Data Index: 1539015 (Python Code)

Max Activating Token Index: 374

Text #19

Max Range: 3.8147. Min Range: -3.8147

Max Act: 2.4774. Min Act: -0.0000

Data Index: 1562694 (Python Code)

Max Activating Token Index: 464