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

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

Neuron 777 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5871. Min Range: -3.5871

Max Act: 3.5871. Min Act: -0.1700

Data Index: 1032696 (C4 (Web Text))

Max Activating Token Index: 796

Text #1

Max Range: 3.5871. Min Range: -3.5871

Max Act: 3.5088. Min Act: -0.1700

Data Index: 1275779 (C4 (Web Text))

Max Activating Token Index: 770

Text #2

Max Range: 3.5871. Min Range: -3.5871

Max Act: 3.5558. Min Act: -0.1700

Data Index: 414220 (C4 (Web Text))

Max Activating Token Index: 938

Text #3

Max Range: 3.5871. Min Range: -3.5871

Max Act: 3.5088. Min Act: -0.1700

Data Index: 868638 (C4 (Web Text))

Max Activating Token Index: 100

Text #4

Max Range: 3.5871. Min Range: -3.5871

Max Act: 3.4931. Min Act: -0.1700

Data Index: 762227 (C4 (Web Text))

Max Activating Token Index: 863

Text #5

Max Range: 3.5871. Min Range: -3.5871

Max Act: 3.4618. Min Act: -0.1700

Data Index: 869617 (C4 (Web Text))

Max Activating Token Index: 204

Text #6

Max Range: 3.5871. Min Range: -3.5871

Max Act: 3.4461. Min Act: -0.1700

Data Index: 212881 (C4 (Web Text))

Max Activating Token Index: 277

Text #7

Max Range: 3.5871. Min Range: -3.5871

Max Act: 3.4461. Min Act: -0.1700

Data Index: 729433 (C4 (Web Text))

Max Activating Token Index: 1017

Text #8

Max Range: 3.5871. Min Range: -3.5871

Max Act: 3.4461. Min Act: -0.1700

Data Index: 36148 (C4 (Web Text))

Max Activating Token Index: 222

Text #9

Max Range: 3.5871. Min Range: -3.5871

Max Act: 3.4148. Min Act: -0.1700

Data Index: 1305236 (C4 (Web Text))

Max Activating Token Index: 815

Text #10

Max Range: 3.5871. Min Range: -3.5871

Max Act: 3.4461. Min Act: -0.1700

Data Index: 528780 (C4 (Web Text))

Max Activating Token Index: 762

Text #11

Max Range: 3.5871. Min Range: -3.5871

Max Act: 3.4618. Min Act: -0.1700

Data Index: 1139436 (C4 (Web Text))

Max Activating Token Index: 660

Text #12

Max Range: 3.5871. Min Range: -3.5871

Max Act: 3.4461. Min Act: -0.1700

Data Index: 180758 (C4 (Web Text))

Max Activating Token Index: 41

Text #13

Max Range: 3.5871. Min Range: -3.5871

Max Act: 3.4148. Min Act: -0.1700

Data Index: 834856 (C4 (Web Text))

Max Activating Token Index: 632

Text #14

Max Range: 3.5871. Min Range: -3.5871

Max Act: 3.4148. Min Act: -0.1700

Data Index: 875843 (C4 (Web Text))

Max Activating Token Index: 323

Text #15

Max Range: 3.5871. Min Range: -3.5871

Max Act: 3.3991. Min Act: -0.1700

Data Index: 1100816 (C4 (Web Text))

Max Activating Token Index: 840

Text #16

Max Range: 3.5871. Min Range: -3.5871

Max Act: 3.3834. Min Act: -0.1700

Data Index: 768832 (C4 (Web Text))

Max Activating Token Index: 736

Text #17

Max Range: 3.5871. Min Range: -3.5871

Max Act: 3.3834. Min Act: -0.1700

Data Index: 332116 (C4 (Web Text))

Max Activating Token Index: 200

Text #18

Max Range: 3.5871. Min Range: -3.5871

Max Act: 3.3991. Min Act: -0.1700

Data Index: 829204 (C4 (Web Text))

Max Activating Token Index: 267

Text #19

Max Range: 3.5871. Min Range: -3.5871

Max Act: 3.4148. Min Act: -0.1700

Data Index: 1245370 (C4 (Web Text))

Max Activating Token Index: 722