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

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

Neuron 3136 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1896. Min Range: -1.1896

Max Act: 1.1896. Min Act: -0.0000

Data Index: 1016543 (C4 (Web Text))

Max Activating Token Index: 723

Text #1

Max Range: 1.1896. Min Range: -1.1896

Max Act: 1.1395. Min Act: -0.0000

Data Index: 951453 (C4 (Web Text))

Max Activating Token Index: 368

Text #2

Max Range: 1.1896. Min Range: -1.1896

Max Act: 1.0276. Min Act: -0.0000

Data Index: 839142 (C4 (Web Text))

Max Activating Token Index: 207

Text #3

Max Range: 1.1896. Min Range: -1.1896

Max Act: 1.0087. Min Act: -0.0000

Data Index: 1221815 (C4 (Web Text))

Max Activating Token Index: 845

Text #4

Max Range: 1.1896. Min Range: -1.1896

Max Act: 1.0456. Min Act: -0.0000

Data Index: 918028 (C4 (Web Text))

Max Activating Token Index: 483

Text #5

Max Range: 1.1896. Min Range: -1.1896

Max Act: 0.8783. Min Act: -0.0000

Data Index: 1268151 (C4 (Web Text))

Max Activating Token Index: 336

Text #6

Max Range: 1.1896. Min Range: -1.1896

Max Act: 0.8105. Min Act: -0.0000

Data Index: 1288702 (C4 (Web Text))

Max Activating Token Index: 265

Text #7

Max Range: 1.1896. Min Range: -1.1896

Max Act: 0.8591. Min Act: -0.0000

Data Index: 1119977 (C4 (Web Text))

Max Activating Token Index: 31

Text #8

Max Range: 1.1896. Min Range: -1.1896

Max Act: 0.8534. Min Act: -0.0000

Data Index: 263109 (C4 (Web Text))

Max Activating Token Index: 437

Text #9

Max Range: 1.1896. Min Range: -1.1896

Max Act: 0.8446. Min Act: -0.0000

Data Index: 882477 (C4 (Web Text))

Max Activating Token Index: 985

Text #10

Max Range: 1.1896. Min Range: -1.1896

Max Act: 0.8543. Min Act: -0.0000

Data Index: 471612 (C4 (Web Text))

Max Activating Token Index: 888

Text #11

Max Range: 1.1896. Min Range: -1.1896

Max Act: 0.8035. Min Act: -0.0000

Data Index: 1337675 (C4 (Web Text))

Max Activating Token Index: 704

Text #12

Max Range: 1.1896. Min Range: -1.1896

Max Act: 0.8236. Min Act: -0.0000

Data Index: 1133361 (C4 (Web Text))

Max Activating Token Index: 847

Text #13

Max Range: 1.1896. Min Range: -1.1896

Max Act: 0.7739. Min Act: -0.0000

Data Index: 415466 (C4 (Web Text))

Max Activating Token Index: 446

Text #14

Max Range: 1.1896. Min Range: -1.1896

Max Act: 0.7691. Min Act: -0.0000

Data Index: 479179 (C4 (Web Text))

Max Activating Token Index: 848

Text #15

Max Range: 1.1896. Min Range: -1.1896

Max Act: 0.7044. Min Act: -0.0000

Data Index: 1327550 (C4 (Web Text))

Max Activating Token Index: 773

Text #16

Max Range: 1.1896. Min Range: -1.1896

Max Act: 0.7620. Min Act: -0.0000

Data Index: 648452 (C4 (Web Text))

Max Activating Token Index: 739

Text #17

Max Range: 1.1896. Min Range: -1.1896

Max Act: 0.7398. Min Act: -0.0000

Data Index: 182550 (C4 (Web Text))

Max Activating Token Index: 297

Text #18

Max Range: 1.1896. Min Range: -1.1896

Max Act: 0.6972. Min Act: -0.0000

Data Index: 180906 (C4 (Web Text))

Max Activating Token Index: 42

Text #19

Max Range: 1.1896. Min Range: -1.1896

Max Act: 0.6938. Min Act: -0.0000

Data Index: 1034654 (C4 (Web Text))

Max Activating Token Index: 885