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

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

Neuron 1068 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: 3.9438. Min Range: -3.9438

Max Act: 3.9438. Min Act: -0.1700

Data Index: 912564 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 3.9438. Min Range: -3.9438

Max Act: 3.8834. Min Act: -0.1700

Data Index: 1350832 (C4 (Web Text))

Max Activating Token Index: 833

Text #2

Max Range: 3.9438. Min Range: -3.9438

Max Act: 3.8847. Min Act: -0.1700

Data Index: 1131968 (C4 (Web Text))

Max Activating Token Index: 62

Text #3

Max Range: 3.9438. Min Range: -3.9438

Max Act: 3.8902. Min Act: -0.1700

Data Index: 1216623 (C4 (Web Text))

Max Activating Token Index: 294

Text #4

Max Range: 3.9438. Min Range: -3.9438

Max Act: 3.8701. Min Act: -0.1700

Data Index: 305942 (C4 (Web Text))

Max Activating Token Index: 174

Text #5

Max Range: 3.9438. Min Range: -3.9438

Max Act: 3.8679. Min Act: -0.1700

Data Index: 56374 (C4 (Web Text))

Max Activating Token Index: 648

Text #6

Max Range: 3.9438. Min Range: -3.9438

Max Act: 3.8563. Min Act: -0.1700

Data Index: 985060 (C4 (Web Text))

Max Activating Token Index: 210

Text #7

Max Range: 3.9438. Min Range: -3.9438

Max Act: 3.8768. Min Act: -0.1700

Data Index: 1038383 (C4 (Web Text))

Max Activating Token Index: 481

Text #8

Max Range: 3.9438. Min Range: -3.9438

Max Act: 3.8244. Min Act: -0.1700

Data Index: 787150 (C4 (Web Text))

Max Activating Token Index: 554

Text #9

Max Range: 3.9438. Min Range: -3.9438

Max Act: 3.8014. Min Act: -0.1700

Data Index: 236200 (C4 (Web Text))

Max Activating Token Index: 665

Text #10

Max Range: 3.9438. Min Range: -3.9438

Max Act: 3.8034. Min Act: -0.1700

Data Index: 812290 (C4 (Web Text))

Max Activating Token Index: 709

Text #11

Max Range: 3.9438. Min Range: -3.9438

Max Act: 3.8185. Min Act: -0.1700

Data Index: 504197 (C4 (Web Text))

Max Activating Token Index: 328

Text #12

Max Range: 3.9438. Min Range: -3.9438

Max Act: 3.7852. Min Act: -0.1700

Data Index: 182760 (C4 (Web Text))

Max Activating Token Index: 988

Text #13

Max Range: 3.9438. Min Range: -3.9438

Max Act: 3.7723. Min Act: -0.1700

Data Index: 326427 (C4 (Web Text))

Max Activating Token Index: 713

Text #14

Max Range: 3.9438. Min Range: -3.9438

Max Act: 3.7743. Min Act: -0.1700

Data Index: 615001 (C4 (Web Text))

Max Activating Token Index: 276

Text #15

Max Range: 3.9438. Min Range: -3.9438

Max Act: 3.7664. Min Act: -0.1700

Data Index: 756538 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 3.9438. Min Range: -3.9438

Max Act: 3.7662. Min Act: -0.1700

Data Index: 394235 (C4 (Web Text))

Max Activating Token Index: 925

Text #17

Max Range: 3.9438. Min Range: -3.9438

Max Act: 3.7588. Min Act: -0.1700

Data Index: 1056148 (C4 (Web Text))

Max Activating Token Index: 905

Text #18

Max Range: 3.9438. Min Range: -3.9438

Max Act: 3.7531. Min Act: -0.1700

Data Index: 800395 (C4 (Web Text))

Max Activating Token Index: 11

Text #19

Max Range: 3.9438. Min Range: -3.9438

Max Act: 3.7724. Min Act: -0.1700

Data Index: 242451 (C4 (Web Text))

Max Activating Token Index: 272