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

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

Neuron 6020 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: 2.9401. Min Range: -2.9401

Max Act: 2.9401. Min Act: -0.0000

Data Index: 649346 (C4 (Web Text))

Max Activating Token Index: 260

Text #1

Max Range: 2.9401. Min Range: -2.9401

Max Act: 2.6298. Min Act: -0.0000

Data Index: 1560800 (Python Code)

Max Activating Token Index: 784

Text #2

Max Range: 2.9401. Min Range: -2.9401

Max Act: 2.7848. Min Act: -0.0000

Data Index: 822391 (C4 (Web Text))

Max Activating Token Index: 66

Text #3

Max Range: 2.9401. Min Range: -2.9401

Max Act: 2.5975. Min Act: -0.0000

Data Index: 1630069 (Python Code)

Max Activating Token Index: 524

Text #4

Max Range: 2.9401. Min Range: -2.9401

Max Act: 2.4084. Min Act: -0.0000

Data Index: 1436941 (Python Code)

Max Activating Token Index: 249

Text #5

Max Range: 2.9401. Min Range: -2.9401

Max Act: 2.6404. Min Act: -0.0000

Data Index: 1392293 (Python Code)

Max Activating Token Index: 746

Text #6

Max Range: 2.9401. Min Range: -2.9401

Max Act: 2.5103. Min Act: -0.0000

Data Index: 1036897 (C4 (Web Text))

Max Activating Token Index: 666

Text #7

Max Range: 2.9401. Min Range: -2.9401

Max Act: 2.4997. Min Act: -0.0000

Data Index: 881586 (C4 (Web Text))

Max Activating Token Index: 75

Text #8

Max Range: 2.9401. Min Range: -2.9401

Max Act: 2.5014. Min Act: -0.0000

Data Index: 697324 (C4 (Web Text))

Max Activating Token Index: 1014

Text #9

Max Range: 2.9401. Min Range: -2.9401

Max Act: 2.4764. Min Act: -0.0000

Data Index: 1630078 (Python Code)

Max Activating Token Index: 9

Text #10

Max Range: 2.9401. Min Range: -2.9401

Max Act: 2.2023. Min Act: -0.0000

Data Index: 455935 (C4 (Web Text))

Max Activating Token Index: 941

Text #11

Max Range: 2.9401. Min Range: -2.9401

Max Act: 2.2716. Min Act: -0.0000

Data Index: 1476655 (Python Code)

Max Activating Token Index: 551

Text #12

Max Range: 2.9401. Min Range: -2.9401

Max Act: 2.5276. Min Act: -0.0000

Data Index: 395083 (C4 (Web Text))

Max Activating Token Index: 672

Text #13

Max Range: 2.9401. Min Range: -2.9401

Max Act: 2.3967. Min Act: -0.0000

Data Index: 509283 (C4 (Web Text))

Max Activating Token Index: 230

Text #14

Max Range: 2.9401. Min Range: -2.9401

Max Act: 2.3263. Min Act: -0.0000

Data Index: 1241404 (C4 (Web Text))

Max Activating Token Index: 559

Text #15

Max Range: 2.9401. Min Range: -2.9401

Max Act: 2.2828. Min Act: -0.0000

Data Index: 283112 (C4 (Web Text))

Max Activating Token Index: 543

Text #16

Max Range: 2.9401. Min Range: -2.9401

Max Act: 2.2582. Min Act: -0.0000

Data Index: 1450004 (Python Code)

Max Activating Token Index: 383

Text #17

Max Range: 2.9401. Min Range: -2.9401

Max Act: 2.1228. Min Act: -0.0000

Data Index: 1058125 (C4 (Web Text))

Max Activating Token Index: 432

Text #18

Max Range: 2.9401. Min Range: -2.9401

Max Act: 2.2125. Min Act: -0.0000

Data Index: 776427 (C4 (Web Text))

Max Activating Token Index: 614

Text #19

Max Range: 2.9401. Min Range: -2.9401

Max Act: 2.0890. Min Act: -0.0000

Data Index: 700093 (C4 (Web Text))

Max Activating Token Index: 324