Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3023 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0060. Min Range: -1.0060

Max Act: 1.0015. Min Act: -0.0000

Data Index: 249327 (C4 (Web Text))

Max Activating Token Index: 903

Text #1

Max Range: 1.0060. Min Range: -1.0060

Max Act: 1.0060. Min Act: -0.0000

Data Index: 1167003 (C4 (Web Text))

Max Activating Token Index: 266

Text #2

Max Range: 1.0060. Min Range: -1.0060

Max Act: 0.7789. Min Act: -0.0000

Data Index: 403822 (C4 (Web Text))

Max Activating Token Index: 857

Text #3

Max Range: 1.0060. Min Range: -1.0060

Max Act: 0.8520. Min Act: -0.0000

Data Index: 272125 (C4 (Web Text))

Max Activating Token Index: 978

Text #4

Max Range: 1.0060. Min Range: -1.0060

Max Act: 0.6943. Min Act: -0.0000

Data Index: 258510 (C4 (Web Text))

Max Activating Token Index: 218

Text #5

Max Range: 1.0060. Min Range: -1.0060

Max Act: 0.6913. Min Act: -0.0000

Data Index: 856798 (C4 (Web Text))

Max Activating Token Index: 378

Text #6

Max Range: 1.0060. Min Range: -1.0060

Max Act: 0.6849. Min Act: -0.0000

Data Index: 1161106 (C4 (Web Text))

Max Activating Token Index: 95

Text #7

Max Range: 1.0060. Min Range: -1.0060

Max Act: 0.7173. Min Act: -0.0000

Data Index: 407824 (C4 (Web Text))

Max Activating Token Index: 471

Text #8

Max Range: 1.0060. Min Range: -1.0060

Max Act: 0.6983. Min Act: -0.0000

Data Index: 245097 (C4 (Web Text))

Max Activating Token Index: 876

Text #9

Max Range: 1.0060. Min Range: -1.0060

Max Act: 0.6363. Min Act: -0.0000

Data Index: 602446 (C4 (Web Text))

Max Activating Token Index: 850

Text #10

Max Range: 1.0060. Min Range: -1.0060

Max Act: 0.6755. Min Act: -0.0000

Data Index: 309689 (C4 (Web Text))

Max Activating Token Index: 949

Text #11

Max Range: 1.0060. Min Range: -1.0060

Max Act: 0.6578. Min Act: -0.0000

Data Index: 439403 (C4 (Web Text))

Max Activating Token Index: 201

Text #12

Max Range: 1.0060. Min Range: -1.0060

Max Act: 0.6755. Min Act: -0.0000

Data Index: 1568521 (Python Code)

Max Activating Token Index: 529

Text #13

Max Range: 1.0060. Min Range: -1.0060

Max Act: 0.6216. Min Act: -0.0000

Data Index: 1093134 (C4 (Web Text))

Max Activating Token Index: 569

Text #14

Max Range: 1.0060. Min Range: -1.0060

Max Act: 0.6776. Min Act: -0.0000

Data Index: 351734 (C4 (Web Text))

Max Activating Token Index: 300

Text #15

Max Range: 1.0060. Min Range: -1.0060

Max Act: 0.6652. Min Act: -0.0000

Data Index: 1550670 (Python Code)

Max Activating Token Index: 295

Text #16

Max Range: 1.0060. Min Range: -1.0060

Max Act: 0.6424. Min Act: -0.0000

Data Index: 913859 (C4 (Web Text))

Max Activating Token Index: 777

Text #17

Max Range: 1.0060. Min Range: -1.0060

Max Act: 0.5762. Min Act: -0.0000

Data Index: 1620179 (Python Code)

Max Activating Token Index: 852

Text #18

Max Range: 1.0060. Min Range: -1.0060

Max Act: 0.6155. Min Act: -0.0000

Data Index: 711954 (C4 (Web Text))

Max Activating Token Index: 45

Text #19

Max Range: 1.0060. Min Range: -1.0060

Max Act: 0.6039. Min Act: -0.0000

Data Index: 228797 (C4 (Web Text))

Max Activating Token Index: 292