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

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

Neuron 684 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1742. Min Range: -5.1742

Max Act: 5.1742. Min Act: -0.1700

Data Index: 1049650 (C4 (Web Text))

Max Activating Token Index: 905

Text #1

Max Range: 5.1742. Min Range: -5.1742

Max Act: 5.1429. Min Act: -0.1700

Data Index: 549472 (C4 (Web Text))

Max Activating Token Index: 929

Text #2

Max Range: 5.1742. Min Range: -5.1742

Max Act: 5.1429. Min Act: -0.1700

Data Index: 273632 (C4 (Web Text))

Max Activating Token Index: 894

Text #3

Max Range: 5.1742. Min Range: -5.1742

Max Act: 5.1429. Min Act: -0.1700

Data Index: 955376 (C4 (Web Text))

Max Activating Token Index: 842

Text #4

Max Range: 5.1742. Min Range: -5.1742

Max Act: 5.0179. Min Act: -0.1700

Data Index: 1236198 (C4 (Web Text))

Max Activating Token Index: 610

Text #5

Max Range: 5.1742. Min Range: -5.1742

Max Act: 5.0179. Min Act: -0.1700

Data Index: 844316 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 5.1742. Min Range: -5.1742

Max Act: 4.9554. Min Act: -0.1700

Data Index: 877392 (C4 (Web Text))

Max Activating Token Index: 887

Text #7

Max Range: 5.1742. Min Range: -5.1742

Max Act: 4.9554. Min Act: -0.1700

Data Index: 36397 (C4 (Web Text))

Max Activating Token Index: 576

Text #8

Max Range: 5.1742. Min Range: -5.1742

Max Act: 4.9242. Min Act: -0.1700

Data Index: 892306 (C4 (Web Text))

Max Activating Token Index: 967

Text #9

Max Range: 5.1742. Min Range: -5.1742

Max Act: 4.9554. Min Act: -0.1700

Data Index: 986152 (C4 (Web Text))

Max Activating Token Index: 736

Text #10

Max Range: 5.1742. Min Range: -5.1742

Max Act: 4.9242. Min Act: -0.1700

Data Index: 792936 (C4 (Web Text))

Max Activating Token Index: 591

Text #11

Max Range: 5.1742. Min Range: -5.1742

Max Act: 4.8929. Min Act: -0.1700

Data Index: 145532 (C4 (Web Text))

Max Activating Token Index: 1017

Text #12

Max Range: 5.1742. Min Range: -5.1742

Max Act: 4.8617. Min Act: -0.1700

Data Index: 807251 (C4 (Web Text))

Max Activating Token Index: 961

Text #13

Max Range: 5.1742. Min Range: -5.1742

Max Act: 4.8617. Min Act: -0.1700

Data Index: 642889 (C4 (Web Text))

Max Activating Token Index: 900

Text #14

Max Range: 5.1742. Min Range: -5.1742

Max Act: 4.8304. Min Act: -0.1700

Data Index: 28364 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 5.1742. Min Range: -5.1742

Max Act: 4.8304. Min Act: -0.1700

Data Index: 1188186 (C4 (Web Text))

Max Activating Token Index: 566

Text #16

Max Range: 5.1742. Min Range: -5.1742

Max Act: 4.8617. Min Act: -0.1700

Data Index: 1146569 (C4 (Web Text))

Max Activating Token Index: 400

Text #17

Max Range: 5.1742. Min Range: -5.1742

Max Act: 4.7992. Min Act: -0.1700

Data Index: 1140253 (C4 (Web Text))

Max Activating Token Index: 437

Text #18

Max Range: 5.1742. Min Range: -5.1742

Max Act: 4.8304. Min Act: -0.1700

Data Index: 1092199 (C4 (Web Text))

Max Activating Token Index: 935

Text #19

Max Range: 5.1742. Min Range: -5.1742

Max Act: 4.8929. Min Act: -0.1700

Data Index: 791027 (C4 (Web Text))

Max Activating Token Index: 677