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

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

Neuron 472 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1032. Min Range: -5.1032

Max Act: 5.1032. Min Act: -0.1700

Data Index: 274644 (C4 (Web Text))

Max Activating Token Index: 228

Text #1

Max Range: 5.1032. Min Range: -5.1032

Max Act: 4.9157. Min Act: -0.1700

Data Index: 343200 (C4 (Web Text))

Max Activating Token Index: 956

Text #2

Max Range: 5.1032. Min Range: -5.1032

Max Act: 4.8220. Min Act: -0.1700

Data Index: 258515 (C4 (Web Text))

Max Activating Token Index: 883

Text #3

Max Range: 5.1032. Min Range: -5.1032

Max Act: 4.7907. Min Act: -0.1700

Data Index: 961090 (C4 (Web Text))

Max Activating Token Index: 909

Text #4

Max Range: 5.1032. Min Range: -5.1032

Max Act: 4.7282. Min Act: -0.1700

Data Index: 447146 (C4 (Web Text))

Max Activating Token Index: 872

Text #5

Max Range: 5.1032. Min Range: -5.1032

Max Act: 4.6970. Min Act: -0.1700

Data Index: 1186647 (C4 (Web Text))

Max Activating Token Index: 921

Text #6

Max Range: 5.1032. Min Range: -5.1032

Max Act: 4.6345. Min Act: -0.1700

Data Index: 173679 (C4 (Web Text))

Max Activating Token Index: 966

Text #7

Max Range: 5.1032. Min Range: -5.1032

Max Act: 4.6345. Min Act: -0.1700

Data Index: 157428 (C4 (Web Text))

Max Activating Token Index: 869

Text #8

Max Range: 5.1032. Min Range: -5.1032

Max Act: 4.7595. Min Act: -0.1700

Data Index: 878658 (C4 (Web Text))

Max Activating Token Index: 849

Text #9

Max Range: 5.1032. Min Range: -5.1032

Max Act: 4.6032. Min Act: -0.1700

Data Index: 193116 (C4 (Web Text))

Max Activating Token Index: 905

Text #10

Max Range: 5.1032. Min Range: -5.1032

Max Act: 4.5407. Min Act: -0.1700

Data Index: 618877 (C4 (Web Text))

Max Activating Token Index: 833

Text #11

Max Range: 5.1032. Min Range: -5.1032

Max Act: 4.6345. Min Act: -0.1700

Data Index: 1076361 (C4 (Web Text))

Max Activating Token Index: 762

Text #12

Max Range: 5.1032. Min Range: -5.1032

Max Act: 4.6657. Min Act: -0.1700

Data Index: 694629 (C4 (Web Text))

Max Activating Token Index: 728

Text #13

Max Range: 5.1032. Min Range: -5.1032

Max Act: 4.7282. Min Act: -0.1700

Data Index: 947156 (C4 (Web Text))

Max Activating Token Index: 880

Text #14

Max Range: 5.1032. Min Range: -5.1032

Max Act: 4.5095. Min Act: -0.1700

Data Index: 552785 (C4 (Web Text))

Max Activating Token Index: 842

Text #15

Max Range: 5.1032. Min Range: -5.1032

Max Act: 4.6345. Min Act: -0.1700

Data Index: 366495 (C4 (Web Text))

Max Activating Token Index: 811

Text #16

Max Range: 5.1032. Min Range: -5.1032

Max Act: 4.5720. Min Act: -0.1700

Data Index: 750853 (C4 (Web Text))

Max Activating Token Index: 268

Text #17

Max Range: 5.1032. Min Range: -5.1032

Max Act: 4.6032. Min Act: -0.1700

Data Index: 1049821 (C4 (Web Text))

Max Activating Token Index: 902

Text #18

Max Range: 5.1032. Min Range: -5.1032

Max Act: 4.6032. Min Act: -0.1700

Data Index: 282551 (C4 (Web Text))

Max Activating Token Index: 705

Text #19

Max Range: 5.1032. Min Range: -5.1032

Max Act: 4.6032. Min Act: -0.1700

Data Index: 297095 (C4 (Web Text))

Max Activating Token Index: 20