Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4889 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.3321. Min Act: -0.0000

Data Index: 923094 (C4 (Web Text))

Max Activating Token Index: 786

Text #1

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2580. Min Act: -0.0000

Data Index: 467045 (C4 (Web Text))

Max Activating Token Index: 74

Text #2

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2619. Min Act: -0.0000

Data Index: 1413898 (Python Code)

Max Activating Token Index: 306

Text #3

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2550. Min Act: -0.0000

Data Index: 448875 (C4 (Web Text))

Max Activating Token Index: 529

Text #4

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2506. Min Act: -0.0000

Data Index: 242592 (C4 (Web Text))

Max Activating Token Index: 866

Text #5

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2256. Min Act: -0.0000

Data Index: 1250596 (C4 (Web Text))

Max Activating Token Index: 753

Text #6

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2198. Min Act: -0.0000

Data Index: 118740 (C4 (Web Text))

Max Activating Token Index: 525

Text #7

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2163. Min Act: -0.0000

Data Index: 997825 (C4 (Web Text))

Max Activating Token Index: 504

Text #8

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2076. Min Act: -0.0000

Data Index: 1329505 (C4 (Web Text))

Max Activating Token Index: 285

Text #9

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.1993. Min Act: -0.0000

Data Index: 1198992 (C4 (Web Text))

Max Activating Token Index: 991

Text #10

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.1971. Min Act: -0.0000

Data Index: 1295347 (C4 (Web Text))

Max Activating Token Index: 834

Text #11

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.1895. Min Act: -0.0000

Data Index: 949168 (C4 (Web Text))

Max Activating Token Index: 686

Text #12

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.1883. Min Act: -0.0000

Data Index: 1039500 (C4 (Web Text))

Max Activating Token Index: 378

Text #13

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.1669. Min Act: -0.0000

Data Index: 1364400 (Python Code)

Max Activating Token Index: 953

Text #14

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.1904. Min Act: -0.0000

Data Index: 90621 (C4 (Web Text))

Max Activating Token Index: 458

Text #15

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.1863. Min Act: -0.0000

Data Index: 1156238 (C4 (Web Text))

Max Activating Token Index: 372

Text #16

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.1892. Min Act: -0.0000

Data Index: 1439427 (Python Code)

Max Activating Token Index: 787

Text #17

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.1741. Min Act: -0.0000

Data Index: 515006 (C4 (Web Text))

Max Activating Token Index: 564

Text #18

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.1839. Min Act: -0.0000

Data Index: 80912 (C4 (Web Text))

Max Activating Token Index: 570

Text #19

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.1784. Min Act: -0.0000

Data Index: 1515073 (Python Code)

Max Activating Token Index: 216