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

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

Neuron 4454 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: 3.6696. Min Range: -3.6696

Max Act: 3.6696. Min Act: -0.0000

Data Index: 947424 (C4 (Web Text))

Max Activating Token Index: 145

Text #1

Max Range: 3.6696. Min Range: -3.6696

Max Act: 2.6587. Min Act: -0.0000

Data Index: 783029 (C4 (Web Text))

Max Activating Token Index: 240

Text #2

Max Range: 3.6696. Min Range: -3.6696

Max Act: 2.8694. Min Act: -0.0000

Data Index: 108426 (C4 (Web Text))

Max Activating Token Index: 547

Text #3

Max Range: 3.6696. Min Range: -3.6696

Max Act: 2.8723. Min Act: -0.0000

Data Index: 1313473 (C4 (Web Text))

Max Activating Token Index: 278

Text #4

Max Range: 3.6696. Min Range: -3.6696

Max Act: 2.6243. Min Act: -0.0000

Data Index: 805438 (C4 (Web Text))

Max Activating Token Index: 559

Text #5

Max Range: 3.6696. Min Range: -3.6696

Max Act: 2.6964. Min Act: -0.0000

Data Index: 851103 (C4 (Web Text))

Max Activating Token Index: 56

Text #6

Max Range: 3.6696. Min Range: -3.6696

Max Act: 2.5928. Min Act: -0.0000

Data Index: 886513 (C4 (Web Text))

Max Activating Token Index: 259

Text #7

Max Range: 3.6696. Min Range: -3.6696

Max Act: 2.4836. Min Act: -0.0000

Data Index: 1349113 (C4 (Web Text))

Max Activating Token Index: 667

Text #8

Max Range: 3.6696. Min Range: -3.6696

Max Act: 2.5825. Min Act: -0.0000

Data Index: 909052 (C4 (Web Text))

Max Activating Token Index: 478

Text #9

Max Range: 3.6696. Min Range: -3.6696

Max Act: 2.4784. Min Act: -0.0000

Data Index: 781310 (C4 (Web Text))

Max Activating Token Index: 975

Text #10

Max Range: 3.6696. Min Range: -3.6696

Max Act: 2.3262. Min Act: -0.0000

Data Index: 564816 (C4 (Web Text))

Max Activating Token Index: 338

Text #11

Max Range: 3.6696. Min Range: -3.6696

Max Act: 2.3387. Min Act: -0.0000

Data Index: 214831 (C4 (Web Text))

Max Activating Token Index: 849

Text #12

Max Range: 3.6696. Min Range: -3.6696

Max Act: 2.3151. Min Act: -0.0000

Data Index: 1316894 (C4 (Web Text))

Max Activating Token Index: 211

Text #13

Max Range: 3.6696. Min Range: -3.6696

Max Act: 2.4055. Min Act: -0.0000

Data Index: 884045 (C4 (Web Text))

Max Activating Token Index: 236

Text #14

Max Range: 3.6696. Min Range: -3.6696

Max Act: 2.3605. Min Act: -0.0000

Data Index: 772691 (C4 (Web Text))

Max Activating Token Index: 294

Text #15

Max Range: 3.6696. Min Range: -3.6696

Max Act: 2.0908. Min Act: -0.0000

Data Index: 702189 (C4 (Web Text))

Max Activating Token Index: 130

Text #16

Max Range: 3.6696. Min Range: -3.6696

Max Act: 2.3017. Min Act: -0.0000

Data Index: 1161946 (C4 (Web Text))

Max Activating Token Index: 308

Text #17

Max Range: 3.6696. Min Range: -3.6696

Max Act: 2.1692. Min Act: -0.0000

Data Index: 601266 (C4 (Web Text))

Max Activating Token Index: 306

Text #18

Max Range: 3.6696. Min Range: -3.6696

Max Act: 2.2900. Min Act: -0.0000

Data Index: 268379 (C4 (Web Text))

Max Activating Token Index: 330

Text #19

Max Range: 3.6696. Min Range: -3.6696

Max Act: 2.1587. Min Act: -0.0000

Data Index: 684445 (C4 (Web Text))

Max Activating Token Index: 532