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

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

Neuron 1884 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4911. Min Range: -3.4911

Max Act: 3.4911. Min Act: -0.1700

Data Index: 326600 (C4 (Web Text))

Max Activating Token Index: 762

Text #1

Max Range: 3.4911. Min Range: -3.4911

Max Act: 3.4911. Min Act: -0.1700

Data Index: 99622 (C4 (Web Text))

Max Activating Token Index: 649

Text #2

Max Range: 3.4911. Min Range: -3.4911

Max Act: 3.4598. Min Act: -0.1699

Data Index: 1202177 (C4 (Web Text))

Max Activating Token Index: 627

Text #3

Max Range: 3.4911. Min Range: -3.4911

Max Act: 3.4598. Min Act: -0.1700

Data Index: 567449 (C4 (Web Text))

Max Activating Token Index: 999

Text #4

Max Range: 3.4911. Min Range: -3.4911

Max Act: 3.4598. Min Act: -0.1700

Data Index: 732936 (C4 (Web Text))

Max Activating Token Index: 842

Text #5

Max Range: 3.4911. Min Range: -3.4911

Max Act: 3.4598. Min Act: -0.1700

Data Index: 1243323 (C4 (Web Text))

Max Activating Token Index: 773

Text #6

Max Range: 3.4911. Min Range: -3.4911

Max Act: 3.4284. Min Act: -0.1700

Data Index: 490349 (C4 (Web Text))

Max Activating Token Index: 783

Text #7

Max Range: 3.4911. Min Range: -3.4911

Max Act: 3.4284. Min Act: -0.1700

Data Index: 753237 (C4 (Web Text))

Max Activating Token Index: 801

Text #8

Max Range: 3.4911. Min Range: -3.4911

Max Act: 3.4284. Min Act: -0.1700

Data Index: 923383 (C4 (Web Text))

Max Activating Token Index: 762

Text #9

Max Range: 3.4911. Min Range: -3.4911

Max Act: 3.4284. Min Act: -0.1700

Data Index: 1029044 (C4 (Web Text))

Max Activating Token Index: 544

Text #10

Max Range: 3.4911. Min Range: -3.4911

Max Act: 3.3971. Min Act: -0.1700

Data Index: 1072189 (C4 (Web Text))

Max Activating Token Index: 889

Text #11

Max Range: 3.4911. Min Range: -3.4911

Max Act: 3.4284. Min Act: -0.1699

Data Index: 665582 (C4 (Web Text))

Max Activating Token Index: 615

Text #12

Max Range: 3.4911. Min Range: -3.4911

Max Act: 3.3971. Min Act: -0.1699

Data Index: 706983 (C4 (Web Text))

Max Activating Token Index: 641

Text #13

Max Range: 3.4911. Min Range: -3.4911

Max Act: 3.3971. Min Act: -0.1700

Data Index: 785006 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 3.4911. Min Range: -3.4911

Max Act: 3.3971. Min Act: -0.1700

Data Index: 157042 (C4 (Web Text))

Max Activating Token Index: 720

Text #15

Max Range: 3.4911. Min Range: -3.4911

Max Act: 3.4284. Min Act: -0.1700

Data Index: 312381 (C4 (Web Text))

Max Activating Token Index: 838

Text #16

Max Range: 3.4911. Min Range: -3.4911

Max Act: 3.3971. Min Act: -0.1700

Data Index: 972475 (C4 (Web Text))

Max Activating Token Index: 683

Text #17

Max Range: 3.4911. Min Range: -3.4911

Max Act: 3.3971. Min Act: -0.1700

Data Index: 4926 (C4 (Web Text))

Max Activating Token Index: 541

Text #18

Max Range: 3.4911. Min Range: -3.4911

Max Act: 3.3971. Min Act: -0.1698

Data Index: 976156 (C4 (Web Text))

Max Activating Token Index: 572

Text #19

Max Range: 3.4911. Min Range: -3.4911

Max Act: 3.3971. Min Act: -0.1700

Data Index: 1199912 (C4 (Web Text))

Max Activating Token Index: 804