Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1118 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.0449. Min Range: -4.0449

Max Act: 4.0449. Min Act: -0.1700

Data Index: 1099653 (C4 (Web Text))

Max Activating Token Index: 572

Text #1

Max Range: 4.0449. Min Range: -4.0449

Max Act: 4.0073. Min Act: -0.1700

Data Index: 1244686 (C4 (Web Text))

Max Activating Token Index: 107

Text #2

Max Range: 4.0449. Min Range: -4.0449

Max Act: 3.9397. Min Act: -0.1700

Data Index: 1335977 (C4 (Web Text))

Max Activating Token Index: 294

Text #3

Max Range: 4.0449. Min Range: -4.0449

Max Act: 3.8631. Min Act: -0.1700

Data Index: 432824 (C4 (Web Text))

Max Activating Token Index: 316

Text #4

Max Range: 4.0449. Min Range: -4.0449

Max Act: 3.8892. Min Act: -0.1700

Data Index: 434514 (C4 (Web Text))

Max Activating Token Index: 831

Text #5

Max Range: 4.0449. Min Range: -4.0449

Max Act: 3.8546. Min Act: -0.1700

Data Index: 1073113 (C4 (Web Text))

Max Activating Token Index: 945

Text #6

Max Range: 4.0449. Min Range: -4.0449

Max Act: 3.8320. Min Act: -0.1700

Data Index: 158631 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 4.0449. Min Range: -4.0449

Max Act: 3.7859. Min Act: -0.1700

Data Index: 956467 (C4 (Web Text))

Max Activating Token Index: 197

Text #8

Max Range: 4.0449. Min Range: -4.0449

Max Act: 3.8111. Min Act: -0.1700

Data Index: 29773 (C4 (Web Text))

Max Activating Token Index: 313

Text #9

Max Range: 4.0449. Min Range: -4.0449

Max Act: 3.7600. Min Act: -0.1700

Data Index: 285552 (C4 (Web Text))

Max Activating Token Index: 634

Text #10

Max Range: 4.0449. Min Range: -4.0449

Max Act: 3.7790. Min Act: -0.1700

Data Index: 112180 (C4 (Web Text))

Max Activating Token Index: 941

Text #11

Max Range: 4.0449. Min Range: -4.0449

Max Act: 3.7064. Min Act: -0.1700

Data Index: 137669 (C4 (Web Text))

Max Activating Token Index: 465

Text #12

Max Range: 4.0449. Min Range: -4.0449

Max Act: 3.6948. Min Act: -0.1700

Data Index: 303655 (C4 (Web Text))

Max Activating Token Index: 777

Text #13

Max Range: 4.0449. Min Range: -4.0449

Max Act: 3.6877. Min Act: -0.1700

Data Index: 370457 (C4 (Web Text))

Max Activating Token Index: 633

Text #14

Max Range: 4.0449. Min Range: -4.0449

Max Act: 3.6871. Min Act: -0.1700

Data Index: 1447200 (Python Code)

Max Activating Token Index: 177

Text #15

Max Range: 4.0449. Min Range: -4.0449

Max Act: 3.6419. Min Act: -0.1700

Data Index: 979162 (C4 (Web Text))

Max Activating Token Index: 849

Text #16

Max Range: 4.0449. Min Range: -4.0449

Max Act: 3.6269. Min Act: -0.1700

Data Index: 1163746 (C4 (Web Text))

Max Activating Token Index: 595

Text #17

Max Range: 4.0449. Min Range: -4.0449

Max Act: 3.6490. Min Act: -0.1700

Data Index: 1150984 (C4 (Web Text))

Max Activating Token Index: 453

Text #18

Max Range: 4.0449. Min Range: -4.0449

Max Act: 3.5897. Min Act: -0.1700

Data Index: 919415 (C4 (Web Text))

Max Activating Token Index: 102

Text #19

Max Range: 4.0449. Min Range: -4.0449

Max Act: 3.6048. Min Act: -0.1700

Data Index: 1140816 (C4 (Web Text))

Max Activating Token Index: 109