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

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

Neuron 966 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: 3.5711. Min Range: -3.5711

Max Act: 3.5711. Min Act: -0.1700

Data Index: 890007 (C4 (Web Text))

Max Activating Token Index: 645

Text #1

Max Range: 3.5711. Min Range: -3.5711

Max Act: 3.4771. Min Act: -0.1700

Data Index: 431441 (C4 (Web Text))

Max Activating Token Index: 981

Text #2

Max Range: 3.5711. Min Range: -3.5711

Max Act: 3.4457. Min Act: -0.1700

Data Index: 1125169 (C4 (Web Text))

Max Activating Token Index: 916

Text #3

Max Range: 3.5711. Min Range: -3.5711

Max Act: 3.4771. Min Act: -0.1700

Data Index: 1318085 (C4 (Web Text))

Max Activating Token Index: 974

Text #4

Max Range: 3.5711. Min Range: -3.5711

Max Act: 3.4457. Min Act: -0.1700

Data Index: 818957 (C4 (Web Text))

Max Activating Token Index: 987

Text #5

Max Range: 3.5711. Min Range: -3.5711

Max Act: 3.4144. Min Act: -0.1700

Data Index: 257617 (C4 (Web Text))

Max Activating Token Index: 669

Text #6

Max Range: 3.5711. Min Range: -3.5711

Max Act: 3.4457. Min Act: -0.1700

Data Index: 522812 (C4 (Web Text))

Max Activating Token Index: 874

Text #7

Max Range: 3.5711. Min Range: -3.5711

Max Act: 3.3830. Min Act: -0.1700

Data Index: 1352758 (C4 (Web Text))

Max Activating Token Index: 827

Text #8

Max Range: 3.5711. Min Range: -3.5711

Max Act: 3.3830. Min Act: -0.1700

Data Index: 418776 (C4 (Web Text))

Max Activating Token Index: 914

Text #9

Max Range: 3.5711. Min Range: -3.5711

Max Act: 3.3830. Min Act: -0.1700

Data Index: 1067934 (C4 (Web Text))

Max Activating Token Index: 984

Text #10

Max Range: 3.5711. Min Range: -3.5711

Max Act: 3.4144. Min Act: -0.1700

Data Index: 247137 (C4 (Web Text))

Max Activating Token Index: 1004

Text #11

Max Range: 3.5711. Min Range: -3.5711

Max Act: 3.3830. Min Act: -0.1700

Data Index: 115224 (C4 (Web Text))

Max Activating Token Index: 588

Text #12

Max Range: 3.5711. Min Range: -3.5711

Max Act: 3.3516. Min Act: -0.1700

Data Index: 262046 (C4 (Web Text))

Max Activating Token Index: 986

Text #13

Max Range: 3.5711. Min Range: -3.5711

Max Act: 3.3516. Min Act: -0.1700

Data Index: 240422 (C4 (Web Text))

Max Activating Token Index: 875

Text #14

Max Range: 3.5711. Min Range: -3.5711

Max Act: 3.3202. Min Act: -0.1700

Data Index: 578456 (C4 (Web Text))

Max Activating Token Index: 611

Text #15

Max Range: 3.5711. Min Range: -3.5711

Max Act: 3.3202. Min Act: -0.1700

Data Index: 1097501 (C4 (Web Text))

Max Activating Token Index: 1005

Text #16

Max Range: 3.5711. Min Range: -3.5711

Max Act: 3.3202. Min Act: -0.1700

Data Index: 396411 (C4 (Web Text))

Max Activating Token Index: 462

Text #17

Max Range: 3.5711. Min Range: -3.5711

Max Act: 3.3516. Min Act: -0.1700

Data Index: 347765 (C4 (Web Text))

Max Activating Token Index: 804

Text #18

Max Range: 3.5711. Min Range: -3.5711

Max Act: 3.3516. Min Act: -0.1700

Data Index: 1169779 (C4 (Web Text))

Max Activating Token Index: 469

Text #19

Max Range: 3.5711. Min Range: -3.5711

Max Act: 3.2888. Min Act: -0.1700

Data Index: 1004561 (C4 (Web Text))

Max Activating Token Index: 945