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

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

Neuron 522 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: 0.8789. Min Range: -0.8789

Max Act: 0.8789. Min Act: -0.0000

Data Index: 824961 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 0.8789. Min Range: -0.8789

Max Act: 0.8590. Min Act: -0.0000

Data Index: 1246194 (C4 (Web Text))

Max Activating Token Index: 125

Text #2

Max Range: 0.8789. Min Range: -0.8789

Max Act: 0.8524. Min Act: -0.0000

Data Index: 84216 (C4 (Web Text))

Max Activating Token Index: 947

Text #3

Max Range: 0.8789. Min Range: -0.8789

Max Act: 0.7956. Min Act: -0.0000

Data Index: 525688 (C4 (Web Text))

Max Activating Token Index: 201

Text #4

Max Range: 0.8789. Min Range: -0.8789

Max Act: 0.7844. Min Act: 0.0000

Data Index: 955701 (C4 (Web Text))

Max Activating Token Index: 339

Text #5

Max Range: 0.8789. Min Range: -0.8789

Max Act: 0.7585. Min Act: 0.0000

Data Index: 1161286 (C4 (Web Text))

Max Activating Token Index: 780

Text #6

Max Range: 0.8789. Min Range: -0.8789

Max Act: 0.7468. Min Act: -0.0000

Data Index: 278398 (C4 (Web Text))

Max Activating Token Index: 795

Text #7

Max Range: 0.8789. Min Range: -0.8789

Max Act: 0.7658. Min Act: 0.0000

Data Index: 66718 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 0.8789. Min Range: -0.8789

Max Act: 0.7649. Min Act: -0.0000

Data Index: 147358 (C4 (Web Text))

Max Activating Token Index: 243

Text #9

Max Range: 0.8789. Min Range: -0.8789

Max Act: 0.7494. Min Act: -0.0000

Data Index: 649453 (C4 (Web Text))

Max Activating Token Index: 811

Text #10

Max Range: 0.8789. Min Range: -0.8789

Max Act: 0.7595. Min Act: -0.0000

Data Index: 733327 (C4 (Web Text))

Max Activating Token Index: 278

Text #11

Max Range: 0.8789. Min Range: -0.8789

Max Act: 0.7012. Min Act: -0.0000

Data Index: 195366 (C4 (Web Text))

Max Activating Token Index: 694

Text #12

Max Range: 0.8789. Min Range: -0.8789

Max Act: 0.7031. Min Act: -0.0000

Data Index: 1061920 (C4 (Web Text))

Max Activating Token Index: 404

Text #13

Max Range: 0.8789. Min Range: -0.8789

Max Act: 0.6963. Min Act: -0.0000

Data Index: 359 (C4 (Web Text))

Max Activating Token Index: 911

Text #14

Max Range: 0.8789. Min Range: -0.8789

Max Act: 0.7299. Min Act: -0.0000

Data Index: 1268052 (C4 (Web Text))

Max Activating Token Index: 718

Text #15

Max Range: 0.8789. Min Range: -0.8789

Max Act: 0.6654. Min Act: -0.0000

Data Index: 731548 (C4 (Web Text))

Max Activating Token Index: 621

Text #16

Max Range: 0.8789. Min Range: -0.8789

Max Act: 0.6722. Min Act: -0.0000

Data Index: 1102165 (C4 (Web Text))

Max Activating Token Index: 816

Text #17

Max Range: 0.8789. Min Range: -0.8789

Max Act: 0.6673. Min Act: -0.0000

Data Index: 53544 (C4 (Web Text))

Max Activating Token Index: 77

Text #18

Max Range: 0.8789. Min Range: -0.8789

Max Act: 0.6687. Min Act: -0.0000

Data Index: 1189373 (C4 (Web Text))

Max Activating Token Index: 410

Text #19

Max Range: 0.8789. Min Range: -0.8789

Max Act: 0.6641. Min Act: -0.0000

Data Index: 230489 (C4 (Web Text))

Max Activating Token Index: 176