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

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

Neuron 2046 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.3391. Min Range: -3.3391

Max Act: 3.3391. Min Act: -0.1700

Data Index: 1082329 (C4 (Web Text))

Max Activating Token Index: 542

Text #1

Max Range: 3.3391. Min Range: -3.3391

Max Act: 3.2920. Min Act: -0.1700

Data Index: 961128 (C4 (Web Text))

Max Activating Token Index: 615

Text #2

Max Range: 3.3391. Min Range: -3.3391

Max Act: 3.2763. Min Act: -0.1700

Data Index: 729838 (C4 (Web Text))

Max Activating Token Index: 647

Text #3

Max Range: 3.3391. Min Range: -3.3391

Max Act: 3.2292. Min Act: -0.1700

Data Index: 946000 (C4 (Web Text))

Max Activating Token Index: 50

Text #4

Max Range: 3.3391. Min Range: -3.3391

Max Act: 3.2292. Min Act: -0.1700

Data Index: 214825 (C4 (Web Text))

Max Activating Token Index: 275

Text #5

Max Range: 3.3391. Min Range: -3.3391

Max Act: 3.1977. Min Act: -0.1700

Data Index: 780436 (C4 (Web Text))

Max Activating Token Index: 912

Text #6

Max Range: 3.3391. Min Range: -3.3391

Max Act: 3.1977. Min Act: -0.1700

Data Index: 680274 (C4 (Web Text))

Max Activating Token Index: 445

Text #7

Max Range: 3.3391. Min Range: -3.3391

Max Act: 3.1977. Min Act: -0.1700

Data Index: 112398 (C4 (Web Text))

Max Activating Token Index: 744

Text #8

Max Range: 3.3391. Min Range: -3.3391

Max Act: 3.1977. Min Act: -0.1700

Data Index: 975780 (C4 (Web Text))

Max Activating Token Index: 635

Text #9

Max Range: 3.3391. Min Range: -3.3391

Max Act: 3.1820. Min Act: -0.1700

Data Index: 1124657 (C4 (Web Text))

Max Activating Token Index: 880

Text #10

Max Range: 3.3391. Min Range: -3.3391

Max Act: 3.2134. Min Act: -0.1700

Data Index: 929803 (C4 (Web Text))

Max Activating Token Index: 874

Text #11

Max Range: 3.3391. Min Range: -3.3391

Max Act: 3.2134. Min Act: -0.1700

Data Index: 1308353 (C4 (Web Text))

Max Activating Token Index: 1003

Text #12

Max Range: 3.3391. Min Range: -3.3391

Max Act: 3.2134. Min Act: -0.1700

Data Index: 189061 (C4 (Web Text))

Max Activating Token Index: 571

Text #13

Max Range: 3.3391. Min Range: -3.3391

Max Act: 3.1977. Min Act: -0.1700

Data Index: 480733 (C4 (Web Text))

Max Activating Token Index: 711

Text #14

Max Range: 3.3391. Min Range: -3.3391

Max Act: 3.1820. Min Act: -0.1700

Data Index: 359805 (C4 (Web Text))

Max Activating Token Index: 86

Text #15

Max Range: 3.3391. Min Range: -3.3391

Max Act: 3.1662. Min Act: -0.1700

Data Index: 996308 (C4 (Web Text))

Max Activating Token Index: 345

Text #16

Max Range: 3.3391. Min Range: -3.3391

Max Act: 3.1820. Min Act: -0.1700

Data Index: 881525 (C4 (Web Text))

Max Activating Token Index: 455

Text #17

Max Range: 3.3391. Min Range: -3.3391

Max Act: 3.1505. Min Act: -0.1700

Data Index: 568071 (C4 (Web Text))

Max Activating Token Index: 413

Text #18

Max Range: 3.3391. Min Range: -3.3391

Max Act: 3.1662. Min Act: -0.1700

Data Index: 953193 (C4 (Web Text))

Max Activating Token Index: 408

Text #19

Max Range: 3.3391. Min Range: -3.3391

Max Act: 3.1662. Min Act: -0.1700

Data Index: 624654 (C4 (Web Text))

Max Activating Token Index: 182