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

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

Neuron 1834 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0771. Min Range: -1.0771

Max Act: 1.0771. Min Act: -0.0000

Data Index: 1145093 (C4 (Web Text))

Max Activating Token Index: 904

Text #1

Max Range: 1.0771. Min Range: -1.0771

Max Act: 0.8436. Min Act: -0.0000

Data Index: 841732 (C4 (Web Text))

Max Activating Token Index: 913

Text #2

Max Range: 1.0771. Min Range: -1.0771

Max Act: 0.8388. Min Act: -0.0000

Data Index: 228472 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 1.0771. Min Range: -1.0771

Max Act: 0.8820. Min Act: -0.0000

Data Index: 1287163 (C4 (Web Text))

Max Activating Token Index: 37

Text #4

Max Range: 1.0771. Min Range: -1.0771

Max Act: 0.8409. Min Act: -0.0000

Data Index: 1127891 (C4 (Web Text))

Max Activating Token Index: 41

Text #5

Max Range: 1.0771. Min Range: -1.0771

Max Act: 0.8478. Min Act: -0.0000

Data Index: 420938 (C4 (Web Text))

Max Activating Token Index: 822

Text #6

Max Range: 1.0771. Min Range: -1.0771

Max Act: 0.7943. Min Act: -0.0000

Data Index: 361760 (C4 (Web Text))

Max Activating Token Index: 854

Text #7

Max Range: 1.0771. Min Range: -1.0771

Max Act: 0.8152. Min Act: -0.0000

Data Index: 380650 (C4 (Web Text))

Max Activating Token Index: 37

Text #8

Max Range: 1.0771. Min Range: -1.0771

Max Act: 0.8050. Min Act: -0.0000

Data Index: 324970 (C4 (Web Text))

Max Activating Token Index: 413

Text #9

Max Range: 1.0771. Min Range: -1.0771

Max Act: 0.7753. Min Act: -0.0000

Data Index: 877316 (C4 (Web Text))

Max Activating Token Index: 981

Text #10

Max Range: 1.0771. Min Range: -1.0771

Max Act: 0.8023. Min Act: -0.0000

Data Index: 433219 (C4 (Web Text))

Max Activating Token Index: 31

Text #11

Max Range: 1.0771. Min Range: -1.0771

Max Act: 0.7958. Min Act: -0.0000

Data Index: 1483978 (Python Code)

Max Activating Token Index: 553

Text #12

Max Range: 1.0771. Min Range: -1.0771

Max Act: 0.7798. Min Act: -0.0000

Data Index: 307705 (C4 (Web Text))

Max Activating Token Index: 215

Text #13

Max Range: 1.0771. Min Range: -1.0771

Max Act: 0.7807. Min Act: -0.0000

Data Index: 227344 (C4 (Web Text))

Max Activating Token Index: 843

Text #14

Max Range: 1.0771. Min Range: -1.0771

Max Act: 0.7782. Min Act: -0.0000

Data Index: 1015961 (C4 (Web Text))

Max Activating Token Index: 319

Text #15

Max Range: 1.0771. Min Range: -1.0771

Max Act: 0.7956. Min Act: -0.0000

Data Index: 1233867 (C4 (Web Text))

Max Activating Token Index: 109

Text #16

Max Range: 1.0771. Min Range: -1.0771

Max Act: 0.7673. Min Act: -0.0000

Data Index: 1153151 (C4 (Web Text))

Max Activating Token Index: 832

Text #17

Max Range: 1.0771. Min Range: -1.0771

Max Act: 0.7614. Min Act: -0.0000

Data Index: 411873 (C4 (Web Text))

Max Activating Token Index: 68

Text #18

Max Range: 1.0771. Min Range: -1.0771

Max Act: 0.7708. Min Act: -0.0000

Data Index: 1553278 (Python Code)

Max Activating Token Index: 195

Text #19

Max Range: 1.0771. Min Range: -1.0771

Max Act: 0.7669. Min Act: -0.0000

Data Index: 545267 (C4 (Web Text))

Max Activating Token Index: 204