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

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

Neuron 1856 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0904. Min Range: -1.0904

Max Act: 1.0904. Min Act: -0.0000

Data Index: 703900 (C4 (Web Text))

Max Activating Token Index: 282

Text #1

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.9645. Min Act: -0.0000

Data Index: 586378 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.8498. Min Act: -0.0000

Data Index: 291329 (C4 (Web Text))

Max Activating Token Index: 652

Text #3

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.7708. Min Act: -0.0000

Data Index: 844261 (C4 (Web Text))

Max Activating Token Index: 111

Text #4

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.8336. Min Act: -0.0000

Data Index: 411482 (C4 (Web Text))

Max Activating Token Index: 912

Text #5

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.7575. Min Act: -0.0000

Data Index: 402368 (C4 (Web Text))

Max Activating Token Index: 194

Text #6

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.7488. Min Act: -0.0000

Data Index: 1351062 (C4 (Web Text))

Max Activating Token Index: 666

Text #7

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.7211. Min Act: -0.0000

Data Index: 937711 (C4 (Web Text))

Max Activating Token Index: 284

Text #8

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.7370. Min Act: -0.0000

Data Index: 1317708 (C4 (Web Text))

Max Activating Token Index: 789

Text #9

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.7382. Min Act: -0.0000

Data Index: 1342762 (C4 (Web Text))

Max Activating Token Index: 592

Text #10

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.7187. Min Act: -0.0000

Data Index: 756592 (C4 (Web Text))

Max Activating Token Index: 233

Text #11

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.7083. Min Act: -0.0000

Data Index: 714376 (C4 (Web Text))

Max Activating Token Index: 504

Text #12

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.6916. Min Act: -0.0000

Data Index: 515476 (C4 (Web Text))

Max Activating Token Index: 245

Text #13

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.7048. Min Act: -0.0000

Data Index: 134525 (C4 (Web Text))

Max Activating Token Index: 470

Text #14

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.6958. Min Act: 0.0000

Data Index: 486299 (C4 (Web Text))

Max Activating Token Index: 101

Text #15

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.6966. Min Act: -0.0000

Data Index: 411270 (C4 (Web Text))

Max Activating Token Index: 485

Text #16

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.6649. Min Act: -0.0000

Data Index: 520801 (C4 (Web Text))

Max Activating Token Index: 978

Text #17

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.6797. Min Act: -0.0000

Data Index: 1048956 (C4 (Web Text))

Max Activating Token Index: 139

Text #18

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.6759. Min Act: -0.0000

Data Index: 455711 (C4 (Web Text))

Max Activating Token Index: 33

Text #19

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.6529. Min Act: -0.0000

Data Index: 710087 (C4 (Web Text))

Max Activating Token Index: 756