Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1699 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.2685. Min Range: -5.2685

Max Act: 5.2685. Min Act: -0.1700

Data Index: 168007 (C4 (Web Text))

Max Activating Token Index: 724

Text #1

Max Range: 5.2685. Min Range: -5.2685

Max Act: 5.2373. Min Act: -0.1700

Data Index: 1032246 (C4 (Web Text))

Max Activating Token Index: 671

Text #2

Max Range: 5.2685. Min Range: -5.2685

Max Act: 5.2373. Min Act: -0.1700

Data Index: 830478 (C4 (Web Text))

Max Activating Token Index: 774

Text #3

Max Range: 5.2685. Min Range: -5.2685

Max Act: 5.1748. Min Act: -0.1700

Data Index: 467459 (C4 (Web Text))

Max Activating Token Index: 972

Text #4

Max Range: 5.2685. Min Range: -5.2685

Max Act: 5.1123. Min Act: -0.1700

Data Index: 821817 (C4 (Web Text))

Max Activating Token Index: 707

Text #5

Max Range: 5.2685. Min Range: -5.2685

Max Act: 5.1123. Min Act: -0.1700

Data Index: 370026 (C4 (Web Text))

Max Activating Token Index: 489

Text #6

Max Range: 5.2685. Min Range: -5.2685

Max Act: 5.1123. Min Act: -0.1700

Data Index: 759726 (C4 (Web Text))

Max Activating Token Index: 863

Text #7

Max Range: 5.2685. Min Range: -5.2685

Max Act: 5.0810. Min Act: -0.1700

Data Index: 279541 (C4 (Web Text))

Max Activating Token Index: 735

Text #8

Max Range: 5.2685. Min Range: -5.2685

Max Act: 5.1123. Min Act: -0.1700

Data Index: 656897 (C4 (Web Text))

Max Activating Token Index: 637

Text #9

Max Range: 5.2685. Min Range: -5.2685

Max Act: 5.1123. Min Act: -0.1700

Data Index: 253520 (C4 (Web Text))

Max Activating Token Index: 932

Text #10

Max Range: 5.2685. Min Range: -5.2685

Max Act: 5.0810. Min Act: -0.1700

Data Index: 199423 (C4 (Web Text))

Max Activating Token Index: 682

Text #11

Max Range: 5.2685. Min Range: -5.2685

Max Act: 5.0810. Min Act: -0.1700

Data Index: 1114784 (C4 (Web Text))

Max Activating Token Index: 808

Text #12

Max Range: 5.2685. Min Range: -5.2685

Max Act: 5.0185. Min Act: -0.1700

Data Index: 428120 (C4 (Web Text))

Max Activating Token Index: 869

Text #13

Max Range: 5.2685. Min Range: -5.2685

Max Act: 5.0810. Min Act: -0.1700

Data Index: 779098 (C4 (Web Text))

Max Activating Token Index: 691

Text #14

Max Range: 5.2685. Min Range: -5.2685

Max Act: 4.9873. Min Act: -0.1700

Data Index: 1340602 (C4 (Web Text))

Max Activating Token Index: 504

Text #15

Max Range: 5.2685. Min Range: -5.2685

Max Act: 5.0498. Min Act: -0.1700

Data Index: 714804 (C4 (Web Text))

Max Activating Token Index: 844

Text #16

Max Range: 5.2685. Min Range: -5.2685

Max Act: 5.0185. Min Act: -0.1700

Data Index: 457202 (C4 (Web Text))

Max Activating Token Index: 500

Text #17

Max Range: 5.2685. Min Range: -5.2685

Max Act: 5.0498. Min Act: -0.1700

Data Index: 895057 (C4 (Web Text))

Max Activating Token Index: 342

Text #18

Max Range: 5.2685. Min Range: -5.2685

Max Act: 5.0498. Min Act: -0.1700

Data Index: 979463 (C4 (Web Text))

Max Activating Token Index: 571

Text #19

Max Range: 5.2685. Min Range: -5.2685

Max Act: 5.0185. Min Act: -0.1700

Data Index: 149462 (C4 (Web Text))

Max Activating Token Index: 545