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

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

Neuron 1901 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1746. Min Range: -3.1746

Max Act: 3.1589. Min Act: -0.1700

Data Index: 989122 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 3.1746. Min Range: -3.1746

Max Act: 3.1746. Min Act: -0.1700

Data Index: 296793 (C4 (Web Text))

Max Activating Token Index: 505

Text #2

Max Range: 3.1746. Min Range: -3.1746

Max Act: 3.1746. Min Act: -0.1700

Data Index: 1356277 (C4 (Web Text))

Max Activating Token Index: 821

Text #3

Max Range: 3.1746. Min Range: -3.1746

Max Act: 3.1746. Min Act: -0.1700

Data Index: 1448690 (Python Code)

Max Activating Token Index: 9

Text #4

Max Range: 3.1746. Min Range: -3.1746

Max Act: 3.1746. Min Act: -0.1700

Data Index: 754986 (C4 (Web Text))

Max Activating Token Index: 702

Text #5

Max Range: 3.1746. Min Range: -3.1746

Max Act: 3.1431. Min Act: -0.1700

Data Index: 58711 (C4 (Web Text))

Max Activating Token Index: 86

Text #6

Max Range: 3.1746. Min Range: -3.1746

Max Act: 3.1431. Min Act: -0.1700

Data Index: 941867 (C4 (Web Text))

Max Activating Token Index: 338

Text #7

Max Range: 3.1746. Min Range: -3.1746

Max Act: 3.1431. Min Act: -0.1700

Data Index: 45745 (C4 (Web Text))

Max Activating Token Index: 389

Text #8

Max Range: 3.1746. Min Range: -3.1746

Max Act: 3.1431. Min Act: -0.1700

Data Index: 1235410 (C4 (Web Text))

Max Activating Token Index: 646

Text #9

Max Range: 3.1746. Min Range: -3.1746

Max Act: 3.1274. Min Act: -0.1700

Data Index: 263689 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 3.1746. Min Range: -3.1746

Max Act: 3.1274. Min Act: -0.1700

Data Index: 642137 (C4 (Web Text))

Max Activating Token Index: 847

Text #11

Max Range: 3.1746. Min Range: -3.1746

Max Act: 3.1274. Min Act: -0.1700

Data Index: 1090151 (C4 (Web Text))

Max Activating Token Index: 879

Text #12

Max Range: 3.1746. Min Range: -3.1746

Max Act: 3.1274. Min Act: -0.1700

Data Index: 619223 (C4 (Web Text))

Max Activating Token Index: 193

Text #13

Max Range: 3.1746. Min Range: -3.1746

Max Act: 3.1116. Min Act: -0.1700

Data Index: 392120 (C4 (Web Text))

Max Activating Token Index: 615

Text #14

Max Range: 3.1746. Min Range: -3.1746

Max Act: 3.0801. Min Act: -0.1700

Data Index: 929096 (C4 (Web Text))

Max Activating Token Index: 489

Text #15

Max Range: 3.1746. Min Range: -3.1746

Max Act: 3.0801. Min Act: -0.1700

Data Index: 1390726 (Python Code)

Max Activating Token Index: 425

Text #16

Max Range: 3.1746. Min Range: -3.1746

Max Act: 3.0643. Min Act: -0.1700

Data Index: 1436368 (Python Code)

Max Activating Token Index: 794

Text #17

Max Range: 3.1746. Min Range: -3.1746

Max Act: 3.0643. Min Act: -0.1700

Data Index: 1552383 (Python Code)

Max Activating Token Index: 88

Text #18

Max Range: 3.1746. Min Range: -3.1746

Max Act: 3.0327. Min Act: -0.1700

Data Index: 1265811 (C4 (Web Text))

Max Activating Token Index: 378

Text #19

Max Range: 3.1746. Min Range: -3.1746

Max Act: 3.0643. Min Act: -0.1700

Data Index: 1256737 (C4 (Web Text))

Max Activating Token Index: 2