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

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

Neuron 1303 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: 4.1951. Min Range: -4.1951

Max Act: 4.1951. Min Act: -0.1700

Data Index: 798527 (C4 (Web Text))

Max Activating Token Index: 616

Text #1

Max Range: 4.1951. Min Range: -4.1951

Max Act: 4.0856. Min Act: -0.1700

Data Index: 819860 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 4.1951. Min Range: -4.1951

Max Act: 4.0231. Min Act: -0.1700

Data Index: 1183073 (C4 (Web Text))

Max Activating Token Index: 263

Text #3

Max Range: 4.1951. Min Range: -4.1951

Max Act: 4.0856. Min Act: -0.1700

Data Index: 1253082 (C4 (Web Text))

Max Activating Token Index: 941

Text #4

Max Range: 4.1951. Min Range: -4.1951

Max Act: 4.0544. Min Act: -0.1700

Data Index: 625854 (C4 (Web Text))

Max Activating Token Index: 195

Text #5

Max Range: 4.1951. Min Range: -4.1951

Max Act: 3.9919. Min Act: -0.1700

Data Index: 720010 (C4 (Web Text))

Max Activating Token Index: 680

Text #6

Max Range: 4.1951. Min Range: -4.1951

Max Act: 3.9606. Min Act: -0.1700

Data Index: 743566 (C4 (Web Text))

Max Activating Token Index: 1016

Text #7

Max Range: 4.1951. Min Range: -4.1951

Max Act: 3.9137. Min Act: -0.1700

Data Index: 233700 (C4 (Web Text))

Max Activating Token Index: 804

Text #8

Max Range: 4.1951. Min Range: -4.1951

Max Act: 3.8981. Min Act: -0.1700

Data Index: 7360 (C4 (Web Text))

Max Activating Token Index: 788

Text #9

Max Range: 4.1951. Min Range: -4.1951

Max Act: 3.8981. Min Act: -0.1700

Data Index: 926454 (C4 (Web Text))

Max Activating Token Index: 879

Text #10

Max Range: 4.1951. Min Range: -4.1951

Max Act: 3.8824. Min Act: -0.1700

Data Index: 602136 (C4 (Web Text))

Max Activating Token Index: 251

Text #11

Max Range: 4.1951. Min Range: -4.1951

Max Act: 3.8355. Min Act: -0.1700

Data Index: 853606 (C4 (Web Text))

Max Activating Token Index: 477

Text #12

Max Range: 4.1951. Min Range: -4.1951

Max Act: 3.7886. Min Act: -0.1700

Data Index: 1278679 (C4 (Web Text))

Max Activating Token Index: 730

Text #13

Max Range: 4.1951. Min Range: -4.1951

Max Act: 3.8511. Min Act: -0.1700

Data Index: 834153 (C4 (Web Text))

Max Activating Token Index: 979

Text #14

Max Range: 4.1951. Min Range: -4.1951

Max Act: 3.8355. Min Act: -0.1700

Data Index: 561219 (C4 (Web Text))

Max Activating Token Index: 67

Text #15

Max Range: 4.1951. Min Range: -4.1951

Max Act: 3.8199. Min Act: -0.1700

Data Index: 1073041 (C4 (Web Text))

Max Activating Token Index: 767

Text #16

Max Range: 4.1951. Min Range: -4.1951

Max Act: 3.7573. Min Act: -0.1700

Data Index: 891148 (C4 (Web Text))

Max Activating Token Index: 892

Text #17

Max Range: 4.1951. Min Range: -4.1951

Max Act: 3.7729. Min Act: -0.1700

Data Index: 1183153 (C4 (Web Text))

Max Activating Token Index: 80

Text #18

Max Range: 4.1951. Min Range: -4.1951

Max Act: 3.7886. Min Act: -0.1700

Data Index: 700286 (C4 (Web Text))

Max Activating Token Index: 637

Text #19

Max Range: 4.1951. Min Range: -4.1951

Max Act: 3.7729. Min Act: -0.1700

Data Index: 283598 (C4 (Web Text))

Max Activating Token Index: 49