Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1610 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.7097. Min Range: -3.7097

Max Act: 3.7097. Min Act: -0.1700

Data Index: 670237 (C4 (Web Text))

Max Activating Token Index: 340

Text #1

Max Range: 3.7097. Min Range: -3.7097

Max Act: 3.7097. Min Act: -0.1700

Data Index: 1129519 (C4 (Web Text))

Max Activating Token Index: 195

Text #2

Max Range: 3.7097. Min Range: -3.7097

Max Act: 3.6940. Min Act: -0.1700

Data Index: 969474 (C4 (Web Text))

Max Activating Token Index: 297

Text #3

Max Range: 3.7097. Min Range: -3.7097

Max Act: 3.6158. Min Act: -0.1700

Data Index: 175936 (C4 (Web Text))

Max Activating Token Index: 820

Text #4

Max Range: 3.7097. Min Range: -3.7097

Max Act: 3.6471. Min Act: -0.1700

Data Index: 704011 (C4 (Web Text))

Max Activating Token Index: 633

Text #5

Max Range: 3.7097. Min Range: -3.7097

Max Act: 3.6784. Min Act: -0.1700

Data Index: 794379 (C4 (Web Text))

Max Activating Token Index: 868

Text #6

Max Range: 3.7097. Min Range: -3.7097

Max Act: 3.6627. Min Act: -0.1700

Data Index: 1007719 (C4 (Web Text))

Max Activating Token Index: 694

Text #7

Max Range: 3.7097. Min Range: -3.7097

Max Act: 3.6158. Min Act: -0.1700

Data Index: 754530 (C4 (Web Text))

Max Activating Token Index: 897

Text #8

Max Range: 3.7097. Min Range: -3.7097

Max Act: 3.5845. Min Act: -0.1700

Data Index: 584694 (C4 (Web Text))

Max Activating Token Index: 843

Text #9

Max Range: 3.7097. Min Range: -3.7097

Max Act: 3.6314. Min Act: -0.1700

Data Index: 157849 (C4 (Web Text))

Max Activating Token Index: 620

Text #10

Max Range: 3.7097. Min Range: -3.7097

Max Act: 3.6001. Min Act: -0.1700

Data Index: 1270431 (C4 (Web Text))

Max Activating Token Index: 613

Text #11

Max Range: 3.7097. Min Range: -3.7097

Max Act: 3.6001. Min Act: -0.1700

Data Index: 141759 (C4 (Web Text))

Max Activating Token Index: 746

Text #12

Max Range: 3.7097. Min Range: -3.7097

Max Act: 3.6158. Min Act: -0.1700

Data Index: 1260658 (C4 (Web Text))

Max Activating Token Index: 317

Text #13

Max Range: 3.7097. Min Range: -3.7097

Max Act: 3.6001. Min Act: -0.1700

Data Index: 141775 (C4 (Web Text))

Max Activating Token Index: 694

Text #14

Max Range: 3.7097. Min Range: -3.7097

Max Act: 3.6314. Min Act: -0.1700

Data Index: 1320351 (C4 (Web Text))

Max Activating Token Index: 590

Text #15

Max Range: 3.7097. Min Range: -3.7097

Max Act: 3.5531. Min Act: -0.1700

Data Index: 272744 (C4 (Web Text))

Max Activating Token Index: 453

Text #16

Max Range: 3.7097. Min Range: -3.7097

Max Act: 3.6158. Min Act: -0.1699

Data Index: 1261206 (C4 (Web Text))

Max Activating Token Index: 815

Text #17

Max Range: 3.7097. Min Range: -3.7097

Max Act: 3.5845. Min Act: -0.1700

Data Index: 933199 (C4 (Web Text))

Max Activating Token Index: 272

Text #18

Max Range: 3.7097. Min Range: -3.7097

Max Act: 3.6158. Min Act: -0.1700

Data Index: 740460 (C4 (Web Text))

Max Activating Token Index: 471

Text #19

Max Range: 3.7097. Min Range: -3.7097

Max Act: 3.6001. Min Act: -0.1700

Data Index: 633163 (C4 (Web Text))

Max Activating Token Index: 761