Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 952 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.8880. Min Range: -3.8880

Max Act: 3.8880. Min Act: -0.1700

Data Index: 1262722 (C4 (Web Text))

Max Activating Token Index: 872

Text #1

Max Range: 3.8880. Min Range: -3.8880

Max Act: 3.7003. Min Act: -0.1700

Data Index: 255115 (C4 (Web Text))

Max Activating Token Index: 708

Text #2

Max Range: 3.8880. Min Range: -3.8880

Max Act: 3.6690. Min Act: -0.1700

Data Index: 363342 (C4 (Web Text))

Max Activating Token Index: 312

Text #3

Max Range: 3.8880. Min Range: -3.8880

Max Act: 3.6064. Min Act: -0.1700

Data Index: 506958 (C4 (Web Text))

Max Activating Token Index: 671

Text #4

Max Range: 3.8880. Min Range: -3.8880

Max Act: 3.6377. Min Act: -0.1700

Data Index: 1350879 (C4 (Web Text))

Max Activating Token Index: 681

Text #5

Max Range: 3.8880. Min Range: -3.8880

Max Act: 3.6064. Min Act: -0.1700

Data Index: 185757 (C4 (Web Text))

Max Activating Token Index: 531

Text #6

Max Range: 3.8880. Min Range: -3.8880

Max Act: 3.7003. Min Act: -0.1700

Data Index: 483644 (C4 (Web Text))

Max Activating Token Index: 785

Text #7

Max Range: 3.8880. Min Range: -3.8880

Max Act: 3.6377. Min Act: -0.1700

Data Index: 1186168 (C4 (Web Text))

Max Activating Token Index: 654

Text #8

Max Range: 3.8880. Min Range: -3.8880

Max Act: 3.6690. Min Act: -0.1700

Data Index: 239437 (C4 (Web Text))

Max Activating Token Index: 640

Text #9

Max Range: 3.8880. Min Range: -3.8880

Max Act: 3.6690. Min Act: -0.1700

Data Index: 580710 (C4 (Web Text))

Max Activating Token Index: 599

Text #10

Max Range: 3.8880. Min Range: -3.8880

Max Act: 3.6064. Min Act: -0.1700

Data Index: 1296139 (C4 (Web Text))

Max Activating Token Index: 785

Text #11

Max Range: 3.8880. Min Range: -3.8880

Max Act: 3.6064. Min Act: -0.1700

Data Index: 1318065 (C4 (Web Text))

Max Activating Token Index: 364

Text #12

Max Range: 3.8880. Min Range: -3.8880

Max Act: 3.6064. Min Act: -0.1700

Data Index: 815536 (C4 (Web Text))

Max Activating Token Index: 634

Text #13

Max Range: 3.8880. Min Range: -3.8880

Max Act: 3.6690. Min Act: -0.1700

Data Index: 942283 (C4 (Web Text))

Max Activating Token Index: 784

Text #14

Max Range: 3.8880. Min Range: -3.8880

Max Act: 3.6377. Min Act: -0.1700

Data Index: 442108 (C4 (Web Text))

Max Activating Token Index: 92

Text #15

Max Range: 3.8880. Min Range: -3.8880

Max Act: 3.5751. Min Act: -0.1700

Data Index: 143601 (C4 (Web Text))

Max Activating Token Index: 481

Text #16

Max Range: 3.8880. Min Range: -3.8880

Max Act: 3.5751. Min Act: -0.1700

Data Index: 363678 (C4 (Web Text))

Max Activating Token Index: 529

Text #17

Max Range: 3.8880. Min Range: -3.8880

Max Act: 3.5437. Min Act: -0.1700

Data Index: 963888 (C4 (Web Text))

Max Activating Token Index: 902

Text #18

Max Range: 3.8880. Min Range: -3.8880

Max Act: 3.5124. Min Act: -0.1700

Data Index: 49958 (C4 (Web Text))

Max Activating Token Index: 780

Text #19

Max Range: 3.8880. Min Range: -3.8880

Max Act: 3.5751. Min Act: -0.1700

Data Index: 529433 (C4 (Web Text))

Max Activating Token Index: 713