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

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

Neuron 5112 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.8338. Min Range: -0.8338

Max Act: 0.8208. Min Act: -0.0002

Data Index: 241945 (C4 (Web Text))

Max Activating Token Index: 542

Text #1

Max Range: 0.8338. Min Range: -0.8338

Max Act: 0.8207. Min Act: -0.0002

Data Index: 1151987 (C4 (Web Text))

Max Activating Token Index: 56

Text #2

Max Range: 0.8338. Min Range: -0.8338

Max Act: 0.8338. Min Act: -0.0003

Data Index: 406886 (C4 (Web Text))

Max Activating Token Index: 179

Text #3

Max Range: 0.8338. Min Range: -0.8338

Max Act: 0.8009. Min Act: -0.0002

Data Index: 133715 (C4 (Web Text))

Max Activating Token Index: 300

Text #4

Max Range: 0.8338. Min Range: -0.8338

Max Act: 0.7960. Min Act: -0.0002

Data Index: 376787 (C4 (Web Text))

Max Activating Token Index: 537

Text #5

Max Range: 0.8338. Min Range: -0.8338

Max Act: 0.8067. Min Act: -0.0003

Data Index: 289722 (C4 (Web Text))

Max Activating Token Index: 837

Text #6

Max Range: 0.8338. Min Range: -0.8338

Max Act: 0.7931. Min Act: -0.0002

Data Index: 278539 (C4 (Web Text))

Max Activating Token Index: 983

Text #7

Max Range: 0.8338. Min Range: -0.8338

Max Act: 0.7876. Min Act: -0.0002

Data Index: 748322 (C4 (Web Text))

Max Activating Token Index: 649

Text #8

Max Range: 0.8338. Min Range: -0.8338

Max Act: 0.7771. Min Act: -0.0003

Data Index: 176523 (C4 (Web Text))

Max Activating Token Index: 294

Text #9

Max Range: 0.8338. Min Range: -0.8338

Max Act: 0.7701. Min Act: -0.0002

Data Index: 1252152 (C4 (Web Text))

Max Activating Token Index: 444

Text #10

Max Range: 0.8338. Min Range: -0.8338

Max Act: 0.7955. Min Act: -0.0002

Data Index: 1291501 (C4 (Web Text))

Max Activating Token Index: 449

Text #11

Max Range: 0.8338. Min Range: -0.8338

Max Act: 0.7696. Min Act: -0.0002

Data Index: 443904 (C4 (Web Text))

Max Activating Token Index: 290

Text #12

Max Range: 0.8338. Min Range: -0.8338

Max Act: 0.7556. Min Act: -0.0002

Data Index: 967023 (C4 (Web Text))

Max Activating Token Index: 744

Text #13

Max Range: 0.8338. Min Range: -0.8338

Max Act: 0.7569. Min Act: -0.0002

Data Index: 633487 (C4 (Web Text))

Max Activating Token Index: 849

Text #14

Max Range: 0.8338. Min Range: -0.8338

Max Act: 0.7620. Min Act: -0.0002

Data Index: 1274976 (C4 (Web Text))

Max Activating Token Index: 764

Text #15

Max Range: 0.8338. Min Range: -0.8338

Max Act: 0.7760. Min Act: -0.0002

Data Index: 155580 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 0.8338. Min Range: -0.8338

Max Act: 0.7703. Min Act: -0.0002

Data Index: 205402 (C4 (Web Text))

Max Activating Token Index: 249

Text #17

Max Range: 0.8338. Min Range: -0.8338

Max Act: 0.7531. Min Act: -0.0003

Data Index: 822965 (C4 (Web Text))

Max Activating Token Index: 1016

Text #18

Max Range: 0.8338. Min Range: -0.8338

Max Act: 0.7640. Min Act: -0.0002

Data Index: 986047 (C4 (Web Text))

Max Activating Token Index: 288

Text #19

Max Range: 0.8338. Min Range: -0.8338

Max Act: 0.7694. Min Act: -0.0002

Data Index: 1020178 (C4 (Web Text))

Max Activating Token Index: 250