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

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

Neuron 1011 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1384. Min Range: -3.1384

Max Act: 3.1384. Min Act: -0.1700

Data Index: 571514 (C4 (Web Text))

Max Activating Token Index: 906

Text #1

Max Range: 3.1384. Min Range: -3.1384

Max Act: 3.1384. Min Act: -0.1700

Data Index: 1049764 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 3.1384. Min Range: -3.1384

Max Act: 3.1226. Min Act: -0.1700

Data Index: 124527 (C4 (Web Text))

Max Activating Token Index: 675

Text #3

Max Range: 3.1384. Min Range: -3.1384

Max Act: 3.0911. Min Act: -0.1700

Data Index: 340293 (C4 (Web Text))

Max Activating Token Index: 883

Text #4

Max Range: 3.1384. Min Range: -3.1384

Max Act: 3.0753. Min Act: -0.1700

Data Index: 375069 (C4 (Web Text))

Max Activating Token Index: 10

Text #5

Max Range: 3.1384. Min Range: -3.1384

Max Act: 3.0753. Min Act: -0.1700

Data Index: 1006107 (C4 (Web Text))

Max Activating Token Index: 920

Text #6

Max Range: 3.1384. Min Range: -3.1384

Max Act: 3.0753. Min Act: -0.1700

Data Index: 680179 (C4 (Web Text))

Max Activating Token Index: 630

Text #7

Max Range: 3.1384. Min Range: -3.1384

Max Act: 3.0122. Min Act: -0.1700

Data Index: 482778 (C4 (Web Text))

Max Activating Token Index: 595

Text #8

Max Range: 3.1384. Min Range: -3.1384

Max Act: 3.0596. Min Act: -0.1700

Data Index: 208694 (C4 (Web Text))

Max Activating Token Index: 15

Text #9

Max Range: 3.1384. Min Range: -3.1384

Max Act: 3.0280. Min Act: -0.1700

Data Index: 675421 (C4 (Web Text))

Max Activating Token Index: 943

Text #10

Max Range: 3.1384. Min Range: -3.1384

Max Act: 3.0280. Min Act: -0.1700

Data Index: 493354 (C4 (Web Text))

Max Activating Token Index: 904

Text #11

Max Range: 3.1384. Min Range: -3.1384

Max Act: 3.0280. Min Act: -0.1700

Data Index: 499651 (C4 (Web Text))

Max Activating Token Index: 673

Text #12

Max Range: 3.1384. Min Range: -3.1384

Max Act: 3.0438. Min Act: -0.1700

Data Index: 1269855 (C4 (Web Text))

Max Activating Token Index: 668

Text #13

Max Range: 3.1384. Min Range: -3.1384

Max Act: 2.9964. Min Act: -0.1700

Data Index: 876044 (C4 (Web Text))

Max Activating Token Index: 902

Text #14

Max Range: 3.1384. Min Range: -3.1384

Max Act: 3.0438. Min Act: -0.1700

Data Index: 20810 (C4 (Web Text))

Max Activating Token Index: 479

Text #15

Max Range: 3.1384. Min Range: -3.1384

Max Act: 3.0122. Min Act: -0.1700

Data Index: 738270 (C4 (Web Text))

Max Activating Token Index: 738

Text #16

Max Range: 3.1384. Min Range: -3.1384

Max Act: 3.0122. Min Act: -0.1700

Data Index: 1191728 (C4 (Web Text))

Max Activating Token Index: 101

Text #17

Max Range: 3.1384. Min Range: -3.1384

Max Act: 3.0280. Min Act: -0.1700

Data Index: 946109 (C4 (Web Text))

Max Activating Token Index: 833

Text #18

Max Range: 3.1384. Min Range: -3.1384

Max Act: 2.9964. Min Act: -0.1700

Data Index: 127187 (C4 (Web Text))

Max Activating Token Index: 16

Text #19

Max Range: 3.1384. Min Range: -3.1384

Max Act: 2.9964. Min Act: -0.1700

Data Index: 928841 (C4 (Web Text))

Max Activating Token Index: 3