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

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

Neuron 1430 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1108. Min Range: -5.1108

Max Act: 5.1108. Min Act: -0.1700

Data Index: 1083069 (C4 (Web Text))

Max Activating Token Index: 970

Text #1

Max Range: 5.1108. Min Range: -5.1108

Max Act: 4.9858. Min Act: -0.1700

Data Index: 1194977 (C4 (Web Text))

Max Activating Token Index: 812

Text #2

Max Range: 5.1108. Min Range: -5.1108

Max Act: 4.9233. Min Act: -0.1700

Data Index: 760730 (C4 (Web Text))

Max Activating Token Index: 626

Text #3

Max Range: 5.1108. Min Range: -5.1108

Max Act: 4.9546. Min Act: -0.1700

Data Index: 409463 (C4 (Web Text))

Max Activating Token Index: 833

Text #4

Max Range: 5.1108. Min Range: -5.1108

Max Act: 4.9546. Min Act: -0.1700

Data Index: 1061363 (C4 (Web Text))

Max Activating Token Index: 696

Text #5

Max Range: 5.1108. Min Range: -5.1108

Max Act: 4.9233. Min Act: -0.1700

Data Index: 332172 (C4 (Web Text))

Max Activating Token Index: 635

Text #6

Max Range: 5.1108. Min Range: -5.1108

Max Act: 4.8921. Min Act: -0.1700

Data Index: 900112 (C4 (Web Text))

Max Activating Token Index: 949

Text #7

Max Range: 5.1108. Min Range: -5.1108

Max Act: 4.8296. Min Act: -0.1700

Data Index: 314882 (C4 (Web Text))

Max Activating Token Index: 409

Text #8

Max Range: 5.1108. Min Range: -5.1108

Max Act: 4.8608. Min Act: -0.1700

Data Index: 467502 (C4 (Web Text))

Max Activating Token Index: 179

Text #9

Max Range: 5.1108. Min Range: -5.1108

Max Act: 4.8296. Min Act: -0.1700

Data Index: 559251 (C4 (Web Text))

Max Activating Token Index: 75

Text #10

Max Range: 5.1108. Min Range: -5.1108

Max Act: 4.8608. Min Act: -0.1700

Data Index: 435792 (C4 (Web Text))

Max Activating Token Index: 967

Text #11

Max Range: 5.1108. Min Range: -5.1108

Max Act: 4.8608. Min Act: -0.1700

Data Index: 866449 (C4 (Web Text))

Max Activating Token Index: 185

Text #12

Max Range: 5.1108. Min Range: -5.1108

Max Act: 4.8296. Min Act: -0.1700

Data Index: 332816 (C4 (Web Text))

Max Activating Token Index: 202

Text #13

Max Range: 5.1108. Min Range: -5.1108

Max Act: 4.7983. Min Act: -0.1700

Data Index: 744894 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 5.1108. Min Range: -5.1108

Max Act: 4.8296. Min Act: -0.1700

Data Index: 1061604 (C4 (Web Text))

Max Activating Token Index: 696

Text #15

Max Range: 5.1108. Min Range: -5.1108

Max Act: 4.8296. Min Act: -0.1700

Data Index: 1290851 (C4 (Web Text))

Max Activating Token Index: 893

Text #16

Max Range: 5.1108. Min Range: -5.1108

Max Act: 4.7983. Min Act: -0.1700

Data Index: 592816 (C4 (Web Text))

Max Activating Token Index: 847

Text #17

Max Range: 5.1108. Min Range: -5.1108

Max Act: 4.7983. Min Act: -0.1700

Data Index: 509982 (C4 (Web Text))

Max Activating Token Index: 707

Text #18

Max Range: 5.1108. Min Range: -5.1108

Max Act: 4.8608. Min Act: -0.1700

Data Index: 1313917 (C4 (Web Text))

Max Activating Token Index: 184

Text #19

Max Range: 5.1108. Min Range: -5.1108

Max Act: 4.7983. Min Act: -0.1700

Data Index: 860411 (C4 (Web Text))

Max Activating Token Index: 969