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

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

Neuron 887 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6878. Min Range: -3.6878

Max Act: 3.6878. Min Act: -0.1700

Data Index: 1284176 (C4 (Web Text))

Max Activating Token Index: 896

Text #1

Max Range: 3.6878. Min Range: -3.6878

Max Act: 3.5939. Min Act: -0.1700

Data Index: 1199730 (C4 (Web Text))

Max Activating Token Index: 849

Text #2

Max Range: 3.6878. Min Range: -3.6878

Max Act: 3.5783. Min Act: -0.1700

Data Index: 649895 (C4 (Web Text))

Max Activating Token Index: 472

Text #3

Max Range: 3.6878. Min Range: -3.6878

Max Act: 3.5939. Min Act: -0.1700

Data Index: 94618 (C4 (Web Text))

Max Activating Token Index: 558

Text #4

Max Range: 3.6878. Min Range: -3.6878

Max Act: 3.5939. Min Act: -0.1700

Data Index: 645973 (C4 (Web Text))

Max Activating Token Index: 892

Text #5

Max Range: 3.6878. Min Range: -3.6878

Max Act: 3.5469. Min Act: -0.1700

Data Index: 1286141 (C4 (Web Text))

Max Activating Token Index: 870

Text #6

Max Range: 3.6878. Min Range: -3.6878

Max Act: 3.5469. Min Act: -0.1700

Data Index: 1265041 (C4 (Web Text))

Max Activating Token Index: 783

Text #7

Max Range: 3.6878. Min Range: -3.6878

Max Act: 3.4999. Min Act: -0.1700

Data Index: 771160 (C4 (Web Text))

Max Activating Token Index: 763

Text #8

Max Range: 3.6878. Min Range: -3.6878

Max Act: 3.5156. Min Act: -0.1700

Data Index: 369875 (C4 (Web Text))

Max Activating Token Index: 324

Text #9

Max Range: 3.6878. Min Range: -3.6878

Max Act: 3.4843. Min Act: -0.1700

Data Index: 1310775 (C4 (Web Text))

Max Activating Token Index: 324

Text #10

Max Range: 3.6878. Min Range: -3.6878

Max Act: 3.4529. Min Act: -0.1700

Data Index: 1157062 (C4 (Web Text))

Max Activating Token Index: 926

Text #11

Max Range: 3.6878. Min Range: -3.6878

Max Act: 3.4686. Min Act: -0.1700

Data Index: 190231 (C4 (Web Text))

Max Activating Token Index: 893

Text #12

Max Range: 3.6878. Min Range: -3.6878

Max Act: 3.4686. Min Act: -0.1700

Data Index: 1234661 (C4 (Web Text))

Max Activating Token Index: 1003

Text #13

Max Range: 3.6878. Min Range: -3.6878

Max Act: 3.4529. Min Act: -0.1700

Data Index: 1049551 (C4 (Web Text))

Max Activating Token Index: 337

Text #14

Max Range: 3.6878. Min Range: -3.6878

Max Act: 3.4529. Min Act: -0.1700

Data Index: 608269 (C4 (Web Text))

Max Activating Token Index: 601

Text #15

Max Range: 3.6878. Min Range: -3.6878

Max Act: 3.4529. Min Act: -0.1700

Data Index: 10398 (C4 (Web Text))

Max Activating Token Index: 306

Text #16

Max Range: 3.6878. Min Range: -3.6878

Max Act: 3.4529. Min Act: -0.1700

Data Index: 201971 (C4 (Web Text))

Max Activating Token Index: 472

Text #17

Max Range: 3.6878. Min Range: -3.6878

Max Act: 3.4529. Min Act: -0.1700

Data Index: 1294021 (C4 (Web Text))

Max Activating Token Index: 552

Text #18

Max Range: 3.6878. Min Range: -3.6878

Max Act: 3.4372. Min Act: -0.1700

Data Index: 472593 (C4 (Web Text))

Max Activating Token Index: 789

Text #19

Max Range: 3.6878. Min Range: -3.6878

Max Act: 3.4216. Min Act: -0.1700

Data Index: 1111521 (C4 (Web Text))

Max Activating Token Index: 873