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

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

Neuron 1863 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: 3.3141. Min Range: -3.3141

Max Act: 3.3141. Min Act: -0.1700

Data Index: 1275094 (C4 (Web Text))

Max Activating Token Index: 902

Text #1

Max Range: 3.3141. Min Range: -3.3141

Max Act: 3.2198. Min Act: -0.1700

Data Index: 1191704 (C4 (Web Text))

Max Activating Token Index: 684

Text #2

Max Range: 3.3141. Min Range: -3.3141

Max Act: 3.1883. Min Act: -0.1700

Data Index: 322880 (C4 (Web Text))

Max Activating Token Index: 980

Text #3

Max Range: 3.3141. Min Range: -3.3141

Max Act: 3.1883. Min Act: -0.1700

Data Index: 1128881 (C4 (Web Text))

Max Activating Token Index: 615

Text #4

Max Range: 3.3141. Min Range: -3.3141

Max Act: 3.1726. Min Act: -0.1700

Data Index: 559002 (C4 (Web Text))

Max Activating Token Index: 653

Text #5

Max Range: 3.3141. Min Range: -3.3141

Max Act: 3.1568. Min Act: -0.1700

Data Index: 12607 (C4 (Web Text))

Max Activating Token Index: 758

Text #6

Max Range: 3.3141. Min Range: -3.3141

Max Act: 3.1096. Min Act: -0.1700

Data Index: 532059 (C4 (Web Text))

Max Activating Token Index: 613

Text #7

Max Range: 3.3141. Min Range: -3.3141

Max Act: 3.1096. Min Act: -0.1700

Data Index: 854699 (C4 (Web Text))

Max Activating Token Index: 683

Text #8

Max Range: 3.3141. Min Range: -3.3141

Max Act: 3.1096. Min Act: -0.1700

Data Index: 255765 (C4 (Web Text))

Max Activating Token Index: 516

Text #9

Max Range: 3.3141. Min Range: -3.3141

Max Act: 3.1096. Min Act: -0.1700

Data Index: 1343417 (C4 (Web Text))

Max Activating Token Index: 870

Text #10

Max Range: 3.3141. Min Range: -3.3141

Max Act: 3.1096. Min Act: -0.1700

Data Index: 205949 (C4 (Web Text))

Max Activating Token Index: 595

Text #11

Max Range: 3.3141. Min Range: -3.3141

Max Act: 3.1096. Min Act: -0.1700

Data Index: 1233005 (C4 (Web Text))

Max Activating Token Index: 933

Text #12

Max Range: 3.3141. Min Range: -3.3141

Max Act: 3.1096. Min Act: -0.1700

Data Index: 892431 (C4 (Web Text))

Max Activating Token Index: 296

Text #13

Max Range: 3.3141. Min Range: -3.3141

Max Act: 3.0938. Min Act: -0.1700

Data Index: 1048533 (C4 (Web Text))

Max Activating Token Index: 989

Text #14

Max Range: 3.3141. Min Range: -3.3141

Max Act: 3.0622. Min Act: -0.1700

Data Index: 411901 (C4 (Web Text))

Max Activating Token Index: 728

Text #15

Max Range: 3.3141. Min Range: -3.3141

Max Act: 3.0465. Min Act: -0.1700

Data Index: 878200 (C4 (Web Text))

Max Activating Token Index: 598

Text #16

Max Range: 3.3141. Min Range: -3.3141

Max Act: 3.0622. Min Act: -0.1700

Data Index: 831238 (C4 (Web Text))

Max Activating Token Index: 644

Text #17

Max Range: 3.3141. Min Range: -3.3141

Max Act: 3.0465. Min Act: -0.1700

Data Index: 131755 (C4 (Web Text))

Max Activating Token Index: 779

Text #18

Max Range: 3.3141. Min Range: -3.3141

Max Act: 3.1253. Min Act: -0.1700

Data Index: 573925 (C4 (Web Text))

Max Activating Token Index: 667

Text #19

Max Range: 3.3141. Min Range: -3.3141

Max Act: 3.0780. Min Act: -0.1700

Data Index: 548552 (C4 (Web Text))

Max Activating Token Index: 567