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

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

Neuron 5652 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: 3.4017. Min Range: -3.4017

Max Act: 3.4017. Min Act: -0.0000

Data Index: 1149928 (C4 (Web Text))

Max Activating Token Index: 437

Text #1

Max Range: 3.4017. Min Range: -3.4017

Max Act: 3.3968. Min Act: -0.0000

Data Index: 610542 (C4 (Web Text))

Max Activating Token Index: 755

Text #2

Max Range: 3.4017. Min Range: -3.4017

Max Act: 3.1896. Min Act: -0.0000

Data Index: 943052 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 3.4017. Min Range: -3.4017

Max Act: 3.3224. Min Act: -0.0000

Data Index: 207519 (C4 (Web Text))

Max Activating Token Index: 890

Text #4

Max Range: 3.4017. Min Range: -3.4017

Max Act: 3.2053. Min Act: -0.0000

Data Index: 601580 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 3.4017. Min Range: -3.4017

Max Act: 3.1680. Min Act: -0.0000

Data Index: 135078 (C4 (Web Text))

Max Activating Token Index: 280

Text #6

Max Range: 3.4017. Min Range: -3.4017

Max Act: 2.8930. Min Act: -0.0000

Data Index: 1341721 (C4 (Web Text))

Max Activating Token Index: 793

Text #7

Max Range: 3.4017. Min Range: -3.4017

Max Act: 2.9219. Min Act: -0.0000

Data Index: 588197 (C4 (Web Text))

Max Activating Token Index: 575

Text #8

Max Range: 3.4017. Min Range: -3.4017

Max Act: 2.6042. Min Act: -0.0000

Data Index: 1254805 (C4 (Web Text))

Max Activating Token Index: 384

Text #9

Max Range: 3.4017. Min Range: -3.4017

Max Act: 2.7910. Min Act: -0.0000

Data Index: 1320791 (C4 (Web Text))

Max Activating Token Index: 746

Text #10

Max Range: 3.4017. Min Range: -3.4017

Max Act: 2.8998. Min Act: -0.0000

Data Index: 866972 (C4 (Web Text))

Max Activating Token Index: 387

Text #11

Max Range: 3.4017. Min Range: -3.4017

Max Act: 2.8646. Min Act: -0.0000

Data Index: 986898 (C4 (Web Text))

Max Activating Token Index: 85

Text #12

Max Range: 3.4017. Min Range: -3.4017

Max Act: 2.7378. Min Act: -0.0000

Data Index: 1227762 (C4 (Web Text))

Max Activating Token Index: 587

Text #13

Max Range: 3.4017. Min Range: -3.4017

Max Act: 2.5192. Min Act: -0.0000

Data Index: 661605 (C4 (Web Text))

Max Activating Token Index: 358

Text #14

Max Range: 3.4017. Min Range: -3.4017

Max Act: 2.7787. Min Act: -0.0000

Data Index: 239433 (C4 (Web Text))

Max Activating Token Index: 249

Text #15

Max Range: 3.4017. Min Range: -3.4017

Max Act: 2.7902. Min Act: 0.0000

Data Index: 16570 (C4 (Web Text))

Max Activating Token Index: 207

Text #16

Max Range: 3.4017. Min Range: -3.4017

Max Act: 2.7367. Min Act: -0.0000

Data Index: 485593 (C4 (Web Text))

Max Activating Token Index: 710

Text #17

Max Range: 3.4017. Min Range: -3.4017

Max Act: 2.8690. Min Act: -0.0000

Data Index: 1086710 (C4 (Web Text))

Max Activating Token Index: 237

Text #18

Max Range: 3.4017. Min Range: -3.4017

Max Act: 2.7197. Min Act: -0.0000

Data Index: 1107248 (C4 (Web Text))

Max Activating Token Index: 888

Text #19

Max Range: 3.4017. Min Range: -3.4017

Max Act: 2.6510. Min Act: -0.0000

Data Index: 347497 (C4 (Web Text))

Max Activating Token Index: 972