Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 72 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.8093. Min Range: -3.8093

Max Act: 3.8093. Min Act: -0.1700

Data Index: 190705 (C4 (Web Text))

Max Activating Token Index: 531

Text #1

Max Range: 3.8093. Min Range: -3.8093

Max Act: 3.7154. Min Act: -0.1700

Data Index: 493516 (C4 (Web Text))

Max Activating Token Index: 284

Text #2

Max Range: 3.8093. Min Range: -3.8093

Max Act: 3.6998. Min Act: -0.1700

Data Index: 664261 (C4 (Web Text))

Max Activating Token Index: 387

Text #3

Max Range: 3.8093. Min Range: -3.8093

Max Act: 3.6685. Min Act: -0.1700

Data Index: 601521 (C4 (Web Text))

Max Activating Token Index: 673

Text #4

Max Range: 3.8093. Min Range: -3.8093

Max Act: 3.6372. Min Act: -0.1700

Data Index: 464091 (C4 (Web Text))

Max Activating Token Index: 773

Text #5

Max Range: 3.8093. Min Range: -3.8093

Max Act: 3.6215. Min Act: -0.1700

Data Index: 649999 (C4 (Web Text))

Max Activating Token Index: 269

Text #6

Max Range: 3.8093. Min Range: -3.8093

Max Act: 3.6215. Min Act: -0.1700

Data Index: 248780 (C4 (Web Text))

Max Activating Token Index: 954

Text #7

Max Range: 3.8093. Min Range: -3.8093

Max Act: 3.6059. Min Act: -0.1700

Data Index: 266522 (C4 (Web Text))

Max Activating Token Index: 860

Text #8

Max Range: 3.8093. Min Range: -3.8093

Max Act: 3.5746. Min Act: -0.1700

Data Index: 1323912 (C4 (Web Text))

Max Activating Token Index: 967

Text #9

Max Range: 3.8093. Min Range: -3.8093

Max Act: 3.5746. Min Act: -0.1700

Data Index: 40639 (C4 (Web Text))

Max Activating Token Index: 490

Text #10

Max Range: 3.8093. Min Range: -3.8093

Max Act: 3.5746. Min Act: -0.1700

Data Index: 536374 (C4 (Web Text))

Max Activating Token Index: 431

Text #11

Max Range: 3.8093. Min Range: -3.8093

Max Act: 3.6059. Min Act: -0.1700

Data Index: 740910 (C4 (Web Text))

Max Activating Token Index: 274

Text #12

Max Range: 3.8093. Min Range: -3.8093

Max Act: 3.5589. Min Act: -0.1700

Data Index: 566805 (C4 (Web Text))

Max Activating Token Index: 962

Text #13

Max Range: 3.8093. Min Range: -3.8093

Max Act: 3.6372. Min Act: -0.1700

Data Index: 1182285 (C4 (Web Text))

Max Activating Token Index: 896

Text #14

Max Range: 3.8093. Min Range: -3.8093

Max Act: 3.5902. Min Act: -0.1700

Data Index: 1025559 (C4 (Web Text))

Max Activating Token Index: 770

Text #15

Max Range: 3.8093. Min Range: -3.8093

Max Act: 3.5589. Min Act: -0.1700

Data Index: 918686 (C4 (Web Text))

Max Activating Token Index: 973

Text #16

Max Range: 3.8093. Min Range: -3.8093

Max Act: 3.5589. Min Act: -0.1700

Data Index: 1205960 (C4 (Web Text))

Max Activating Token Index: 510

Text #17

Max Range: 3.8093. Min Range: -3.8093

Max Act: 3.5902. Min Act: -0.1700

Data Index: 1261011 (C4 (Web Text))

Max Activating Token Index: 414

Text #18

Max Range: 3.8093. Min Range: -3.8093

Max Act: 3.5746. Min Act: -0.1700

Data Index: 65876 (C4 (Web Text))

Max Activating Token Index: 59

Text #19

Max Range: 3.8093. Min Range: -3.8093

Max Act: 3.5432. Min Act: -0.1700

Data Index: 768402 (C4 (Web Text))

Max Activating Token Index: 290