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

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

Neuron 1052 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3820. Min Range: -3.3820

Max Act: 3.3820. Min Act: -0.1700

Data Index: 687489 (C4 (Web Text))

Max Activating Token Index: 787

Text #1

Max Range: 3.3820. Min Range: -3.3820

Max Act: 3.3506. Min Act: -0.1700

Data Index: 681234 (C4 (Web Text))

Max Activating Token Index: 536

Text #2

Max Range: 3.3820. Min Range: -3.3820

Max Act: 3.3349. Min Act: -0.1700

Data Index: 449472 (C4 (Web Text))

Max Activating Token Index: 19

Text #3

Max Range: 3.3820. Min Range: -3.3820

Max Act: 3.3506. Min Act: -0.1700

Data Index: 1215022 (C4 (Web Text))

Max Activating Token Index: 948

Text #4

Max Range: 3.3820. Min Range: -3.3820

Max Act: 3.3349. Min Act: -0.1700

Data Index: 889947 (C4 (Web Text))

Max Activating Token Index: 769

Text #5

Max Range: 3.3820. Min Range: -3.3820

Max Act: 3.3192. Min Act: -0.1700

Data Index: 816808 (C4 (Web Text))

Max Activating Token Index: 1015

Text #6

Max Range: 3.3820. Min Range: -3.3820

Max Act: 3.3035. Min Act: -0.1700

Data Index: 1126072 (C4 (Web Text))

Max Activating Token Index: 994

Text #7

Max Range: 3.3820. Min Range: -3.3820

Max Act: 3.3192. Min Act: -0.1700

Data Index: 744078 (C4 (Web Text))

Max Activating Token Index: 844

Text #8

Max Range: 3.3820. Min Range: -3.3820

Max Act: 3.2721. Min Act: -0.1700

Data Index: 662175 (C4 (Web Text))

Max Activating Token Index: 989

Text #9

Max Range: 3.3820. Min Range: -3.3820

Max Act: 3.2878. Min Act: -0.1700

Data Index: 1228877 (C4 (Web Text))

Max Activating Token Index: 523

Text #10

Max Range: 3.3820. Min Range: -3.3820

Max Act: 3.2878. Min Act: -0.1700

Data Index: 952500 (C4 (Web Text))

Max Activating Token Index: 702

Text #11

Max Range: 3.3820. Min Range: -3.3820

Max Act: 3.2721. Min Act: -0.1700

Data Index: 1049264 (C4 (Web Text))

Max Activating Token Index: 681

Text #12

Max Range: 3.3820. Min Range: -3.3820

Max Act: 3.2721. Min Act: -0.1700

Data Index: 29802 (C4 (Web Text))

Max Activating Token Index: 720

Text #13

Max Range: 3.3820. Min Range: -3.3820

Max Act: 3.2564. Min Act: -0.1700

Data Index: 1220811 (C4 (Web Text))

Max Activating Token Index: 940

Text #14

Max Range: 3.3820. Min Range: -3.3820

Max Act: 3.2878. Min Act: -0.1700

Data Index: 366583 (C4 (Web Text))

Max Activating Token Index: 350

Text #15

Max Range: 3.3820. Min Range: -3.3820

Max Act: 3.2564. Min Act: -0.1700

Data Index: 931993 (C4 (Web Text))

Max Activating Token Index: 980

Text #16

Max Range: 3.3820. Min Range: -3.3820

Max Act: 3.2721. Min Act: -0.1700

Data Index: 673696 (C4 (Web Text))

Max Activating Token Index: 481

Text #17

Max Range: 3.3820. Min Range: -3.3820

Max Act: 3.2407. Min Act: -0.1700

Data Index: 355110 (C4 (Web Text))

Max Activating Token Index: 682

Text #18

Max Range: 3.3820. Min Range: -3.3820

Max Act: 3.2407. Min Act: -0.1700

Data Index: 207078 (C4 (Web Text))

Max Activating Token Index: 296

Text #19

Max Range: 3.3820. Min Range: -3.3820

Max Act: 3.2564. Min Act: -0.1700

Data Index: 353105 (C4 (Web Text))

Max Activating Token Index: 941