Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 410 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.1231. Min Act: -0.0001

Data Index: 1599582 (Python Code)

Max Activating Token Index: 87

Text #1

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.1038. Min Act: -0.0001

Data Index: 1585369 (Python Code)

Max Activating Token Index: 615

Text #2

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.1099. Min Act: -0.0001

Data Index: 1623654 (Python Code)

Max Activating Token Index: 748

Text #3

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0986. Min Act: -0.0001

Data Index: 1408349 (Python Code)

Max Activating Token Index: 679

Text #4

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0997. Min Act: -0.0001

Data Index: 990713 (C4 (Web Text))

Max Activating Token Index: 33

Text #5

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0969. Min Act: -0.0001

Data Index: 1550797 (Python Code)

Max Activating Token Index: 469

Text #6

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0979. Min Act: -0.0001

Data Index: 1490805 (Python Code)

Max Activating Token Index: 5

Text #7

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0911. Min Act: -0.0001

Data Index: 1491742 (Python Code)

Max Activating Token Index: 71

Text #8

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0939. Min Act: -0.0001

Data Index: 1417784 (Python Code)

Max Activating Token Index: 871

Text #9

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0946. Min Act: -0.0001

Data Index: 1214875 (C4 (Web Text))

Max Activating Token Index: 884

Text #10

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0915. Min Act: -0.0001

Data Index: 636951 (C4 (Web Text))

Max Activating Token Index: 333

Text #11

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0823. Min Act: -0.0001

Data Index: 772391 (C4 (Web Text))

Max Activating Token Index: 579

Text #12

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0950. Min Act: -0.0001

Data Index: 1491879 (Python Code)

Max Activating Token Index: 59

Text #13

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0817. Min Act: -0.0001

Data Index: 1574944 (Python Code)

Max Activating Token Index: 807

Text #14

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0878. Min Act: -0.0001

Data Index: 1445399 (Python Code)

Max Activating Token Index: 411

Text #15

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0829. Min Act: -0.0001

Data Index: 864043 (C4 (Web Text))

Max Activating Token Index: 629

Text #16

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0866. Min Act: -0.0001

Data Index: 468518 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0896. Min Act: -0.0001

Data Index: 17285 (C4 (Web Text))

Max Activating Token Index: 757

Text #18

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0884. Min Act: -0.0001

Data Index: 1441582 (Python Code)

Max Activating Token Index: 978

Text #19

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0917. Min Act: -0.0001

Data Index: 1410281 (Python Code)

Max Activating Token Index: 593