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

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

Neuron 1560 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: 0.2678. Min Range: -0.2678

Max Act: 0.2672. Min Act: -0.0000

Data Index: 455137 (C4 (Web Text))

Max Activating Token Index: 99

Text #1

Max Range: 0.2678. Min Range: -0.2678

Max Act: 0.2678. Min Act: -0.0000

Data Index: 224568 (C4 (Web Text))

Max Activating Token Index: 209

Text #2

Max Range: 0.2678. Min Range: -0.2678

Max Act: 0.2442. Min Act: -0.0000

Data Index: 529412 (C4 (Web Text))

Max Activating Token Index: 100

Text #3

Max Range: 0.2678. Min Range: -0.2678

Max Act: 0.2431. Min Act: 0.0000

Data Index: 12444 (C4 (Web Text))

Max Activating Token Index: 883

Text #4

Max Range: 0.2678. Min Range: -0.2678

Max Act: 0.2253. Min Act: -0.0000

Data Index: 536539 (C4 (Web Text))

Max Activating Token Index: 689

Text #5

Max Range: 0.2678. Min Range: -0.2678

Max Act: 0.2450. Min Act: -0.0000

Data Index: 509411 (C4 (Web Text))

Max Activating Token Index: 349

Text #6

Max Range: 0.2678. Min Range: -0.2678

Max Act: 0.2350. Min Act: -0.0000

Data Index: 163110 (C4 (Web Text))

Max Activating Token Index: 70

Text #7

Max Range: 0.2678. Min Range: -0.2678

Max Act: 0.2279. Min Act: -0.0000

Data Index: 605241 (C4 (Web Text))

Max Activating Token Index: 291

Text #8

Max Range: 0.2678. Min Range: -0.2678

Max Act: 0.2267. Min Act: -0.0000

Data Index: 823769 (C4 (Web Text))

Max Activating Token Index: 988

Text #9

Max Range: 0.2678. Min Range: -0.2678

Max Act: 0.2166. Min Act: -0.0000

Data Index: 582515 (C4 (Web Text))

Max Activating Token Index: 231

Text #10

Max Range: 0.2678. Min Range: -0.2678

Max Act: 0.2159. Min Act: -0.0000

Data Index: 351060 (C4 (Web Text))

Max Activating Token Index: 682

Text #11

Max Range: 0.2678. Min Range: -0.2678

Max Act: 0.2075. Min Act: -0.0000

Data Index: 1005649 (C4 (Web Text))

Max Activating Token Index: 747

Text #12

Max Range: 0.2678. Min Range: -0.2678

Max Act: 0.2020. Min Act: -0.0000

Data Index: 597970 (C4 (Web Text))

Max Activating Token Index: 860

Text #13

Max Range: 0.2678. Min Range: -0.2678

Max Act: 0.2067. Min Act: -0.0000

Data Index: 1055568 (C4 (Web Text))

Max Activating Token Index: 325

Text #14

Max Range: 0.2678. Min Range: -0.2678

Max Act: 0.2062. Min Act: -0.0000

Data Index: 1157865 (C4 (Web Text))

Max Activating Token Index: 720

Text #15

Max Range: 0.2678. Min Range: -0.2678

Max Act: 0.1915. Min Act: -0.0000

Data Index: 968680 (C4 (Web Text))

Max Activating Token Index: 757

Text #16

Max Range: 0.2678. Min Range: -0.2678

Max Act: 0.1962. Min Act: -0.0000

Data Index: 581481 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 0.2678. Min Range: -0.2678

Max Act: 0.1907. Min Act: -0.0000

Data Index: 908199 (C4 (Web Text))

Max Activating Token Index: 861

Text #18

Max Range: 0.2678. Min Range: -0.2678

Max Act: 0.2020. Min Act: -0.0000

Data Index: 806727 (C4 (Web Text))

Max Activating Token Index: 26

Text #19

Max Range: 0.2678. Min Range: -0.2678

Max Act: 0.1867. Min Act: -0.0000

Data Index: 393288 (C4 (Web Text))

Max Activating Token Index: 836