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

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

Neuron 1626 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: 3.7635. Min Range: -3.7635

Max Act: 3.7635. Min Act: -0.1700

Data Index: 210633 (C4 (Web Text))

Max Activating Token Index: 366

Text #1

Max Range: 3.7635. Min Range: -3.7635

Max Act: 3.7010. Min Act: -0.1700

Data Index: 1016302 (C4 (Web Text))

Max Activating Token Index: 828

Text #2

Max Range: 3.7635. Min Range: -3.7635

Max Act: 3.7010. Min Act: -0.1700

Data Index: 364942 (C4 (Web Text))

Max Activating Token Index: 124

Text #3

Max Range: 3.7635. Min Range: -3.7635

Max Act: 3.6697. Min Act: -0.1700

Data Index: 1219469 (C4 (Web Text))

Max Activating Token Index: 640

Text #4

Max Range: 3.7635. Min Range: -3.7635

Max Act: 3.6853. Min Act: -0.1700

Data Index: 994451 (C4 (Web Text))

Max Activating Token Index: 750

Text #5

Max Range: 3.7635. Min Range: -3.7635

Max Act: 3.6697. Min Act: -0.1700

Data Index: 564530 (C4 (Web Text))

Max Activating Token Index: 542

Text #6

Max Range: 3.7635. Min Range: -3.7635

Max Act: 3.6227. Min Act: -0.1700

Data Index: 952751 (C4 (Web Text))

Max Activating Token Index: 142

Text #7

Max Range: 3.7635. Min Range: -3.7635

Max Act: 3.6384. Min Act: -0.1700

Data Index: 525827 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 3.7635. Min Range: -3.7635

Max Act: 3.6384. Min Act: -0.1700

Data Index: 669079 (C4 (Web Text))

Max Activating Token Index: 1000

Text #9

Max Range: 3.7635. Min Range: -3.7635

Max Act: 3.6070. Min Act: -0.1700

Data Index: 933380 (C4 (Web Text))

Max Activating Token Index: 290

Text #10

Max Range: 3.7635. Min Range: -3.7635

Max Act: 3.6070. Min Act: -0.1700

Data Index: 1023888 (C4 (Web Text))

Max Activating Token Index: 925

Text #11

Max Range: 3.7635. Min Range: -3.7635

Max Act: 3.5914. Min Act: -0.1700

Data Index: 828152 (C4 (Web Text))

Max Activating Token Index: 443

Text #12

Max Range: 3.7635. Min Range: -3.7635

Max Act: 3.5914. Min Act: -0.1700

Data Index: 938906 (C4 (Web Text))

Max Activating Token Index: 122

Text #13

Max Range: 3.7635. Min Range: -3.7635

Max Act: 3.6070. Min Act: -0.1700

Data Index: 492267 (C4 (Web Text))

Max Activating Token Index: 115

Text #14

Max Range: 3.7635. Min Range: -3.7635

Max Act: 3.6070. Min Act: -0.1700

Data Index: 1098439 (C4 (Web Text))

Max Activating Token Index: 187

Text #15

Max Range: 3.7635. Min Range: -3.7635

Max Act: 3.5757. Min Act: -0.1700

Data Index: 494351 (C4 (Web Text))

Max Activating Token Index: 58

Text #16

Max Range: 3.7635. Min Range: -3.7635

Max Act: 3.5757. Min Act: -0.1700

Data Index: 1058433 (C4 (Web Text))

Max Activating Token Index: 290

Text #17

Max Range: 3.7635. Min Range: -3.7635

Max Act: 3.5757. Min Act: -0.1700

Data Index: 593875 (C4 (Web Text))

Max Activating Token Index: 453

Text #18

Max Range: 3.7635. Min Range: -3.7635

Max Act: 3.5601. Min Act: -0.1700

Data Index: 185322 (C4 (Web Text))

Max Activating Token Index: 859

Text #19

Max Range: 3.7635. Min Range: -3.7635

Max Act: 3.5757. Min Act: -0.1700

Data Index: 680318 (C4 (Web Text))

Max Activating Token Index: 371