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

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

Neuron 1576 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6605. Min Range: -5.6605

Max Act: 5.6605. Min Act: -0.1700

Data Index: 162255 (C4 (Web Text))

Max Activating Token Index: 795

Text #1

Max Range: 5.6605. Min Range: -5.6605

Max Act: 5.5980. Min Act: -0.1700

Data Index: 43832 (C4 (Web Text))

Max Activating Token Index: 966

Text #2

Max Range: 5.6605. Min Range: -5.6605

Max Act: 5.3948. Min Act: -0.1700

Data Index: 324303 (C4 (Web Text))

Max Activating Token Index: 929

Text #3

Max Range: 5.6605. Min Range: -5.6605

Max Act: 5.5042. Min Act: -0.1700

Data Index: 885080 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 5.6605. Min Range: -5.6605

Max Act: 5.3011. Min Act: -0.1700

Data Index: 222414 (C4 (Web Text))

Max Activating Token Index: 660

Text #5

Max Range: 5.6605. Min Range: -5.6605

Max Act: 5.4261. Min Act: -0.1700

Data Index: 1328051 (C4 (Web Text))

Max Activating Token Index: 904

Text #6

Max Range: 5.6605. Min Range: -5.6605

Max Act: 5.3948. Min Act: -0.1700

Data Index: 284633 (C4 (Web Text))

Max Activating Token Index: 742

Text #7

Max Range: 5.6605. Min Range: -5.6605

Max Act: 5.3792. Min Act: -0.1700

Data Index: 1328598 (C4 (Web Text))

Max Activating Token Index: 658

Text #8

Max Range: 5.6605. Min Range: -5.6605

Max Act: 5.3948. Min Act: -0.1700

Data Index: 916938 (C4 (Web Text))

Max Activating Token Index: 906

Text #9

Max Range: 5.6605. Min Range: -5.6605

Max Act: 5.3011. Min Act: -0.1700

Data Index: 1327726 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 5.6605. Min Range: -5.6605

Max Act: 5.3948. Min Act: -0.1700

Data Index: 1041885 (C4 (Web Text))

Max Activating Token Index: 737

Text #11

Max Range: 5.6605. Min Range: -5.6605

Max Act: 5.3480. Min Act: -0.1700

Data Index: 771654 (C4 (Web Text))

Max Activating Token Index: 749

Text #12

Max Range: 5.6605. Min Range: -5.6605

Max Act: 5.4105. Min Act: -0.1700

Data Index: 74576 (C4 (Web Text))

Max Activating Token Index: 920

Text #13

Max Range: 5.6605. Min Range: -5.6605

Max Act: 5.3636. Min Act: -0.1700

Data Index: 774889 (C4 (Web Text))

Max Activating Token Index: 571

Text #14

Max Range: 5.6605. Min Range: -5.6605

Max Act: 5.2386. Min Act: -0.1700

Data Index: 534137 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 5.6605. Min Range: -5.6605

Max Act: 5.3011. Min Act: -0.1700

Data Index: 1289543 (C4 (Web Text))

Max Activating Token Index: 872

Text #16

Max Range: 5.6605. Min Range: -5.6605

Max Act: 5.3167. Min Act: -0.1700

Data Index: 1126779 (C4 (Web Text))

Max Activating Token Index: 541

Text #17

Max Range: 5.6605. Min Range: -5.6605

Max Act: 5.2855. Min Act: -0.1700

Data Index: 1138852 (C4 (Web Text))

Max Activating Token Index: 821

Text #18

Max Range: 5.6605. Min Range: -5.6605

Max Act: 5.3323. Min Act: -0.1700

Data Index: 569168 (C4 (Web Text))

Max Activating Token Index: 738

Text #19

Max Range: 5.6605. Min Range: -5.6605

Max Act: 5.3948. Min Act: -0.1700

Data Index: 685991 (C4 (Web Text))

Max Activating Token Index: 570