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

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

Neuron 470 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: 5.3276. Min Range: -5.3276

Max Act: 5.2964. Min Act: -0.1700

Data Index: 481915 (C4 (Web Text))

Max Activating Token Index: 452

Text #1

Max Range: 5.3276. Min Range: -5.3276

Max Act: 5.2964. Min Act: -0.1700

Data Index: 347647 (C4 (Web Text))

Max Activating Token Index: 149

Text #2

Max Range: 5.3276. Min Range: -5.3276

Max Act: 5.3276. Min Act: -0.1700

Data Index: 782370 (C4 (Web Text))

Max Activating Token Index: 466

Text #3

Max Range: 5.3276. Min Range: -5.3276

Max Act: 5.3276. Min Act: -0.1700

Data Index: 530587 (C4 (Web Text))

Max Activating Token Index: 736

Text #4

Max Range: 5.3276. Min Range: -5.3276

Max Act: 5.2651. Min Act: -0.1700

Data Index: 81615 (C4 (Web Text))

Max Activating Token Index: 954

Text #5

Max Range: 5.3276. Min Range: -5.3276

Max Act: 5.2651. Min Act: -0.1700

Data Index: 680539 (C4 (Web Text))

Max Activating Token Index: 595

Text #6

Max Range: 5.3276. Min Range: -5.3276

Max Act: 5.2339. Min Act: -0.1700

Data Index: 1012949 (C4 (Web Text))

Max Activating Token Index: 529

Text #7

Max Range: 5.3276. Min Range: -5.3276

Max Act: 5.2651. Min Act: -0.1700

Data Index: 128308 (C4 (Web Text))

Max Activating Token Index: 93

Text #8

Max Range: 5.3276. Min Range: -5.3276

Max Act: 5.2026. Min Act: -0.1700

Data Index: 1354814 (C4 (Web Text))

Max Activating Token Index: 619

Text #9

Max Range: 5.3276. Min Range: -5.3276

Max Act: 5.2026. Min Act: -0.1700

Data Index: 171793 (C4 (Web Text))

Max Activating Token Index: 654

Text #10

Max Range: 5.3276. Min Range: -5.3276

Max Act: 5.1401. Min Act: -0.1700

Data Index: 602836 (C4 (Web Text))

Max Activating Token Index: 752

Text #11

Max Range: 5.3276. Min Range: -5.3276

Max Act: 5.1401. Min Act: -0.1700

Data Index: 1197297 (C4 (Web Text))

Max Activating Token Index: 875

Text #12

Max Range: 5.3276. Min Range: -5.3276

Max Act: 5.1401. Min Act: -0.1700

Data Index: 1044879 (C4 (Web Text))

Max Activating Token Index: 963

Text #13

Max Range: 5.3276. Min Range: -5.3276

Max Act: 5.1401. Min Act: -0.1700

Data Index: 840126 (C4 (Web Text))

Max Activating Token Index: 197

Text #14

Max Range: 5.3276. Min Range: -5.3276

Max Act: 5.1714. Min Act: -0.1700

Data Index: 577616 (C4 (Web Text))

Max Activating Token Index: 219

Text #15

Max Range: 5.3276. Min Range: -5.3276

Max Act: 5.0464. Min Act: -0.1700

Data Index: 418585 (C4 (Web Text))

Max Activating Token Index: 351

Text #16

Max Range: 5.3276. Min Range: -5.3276

Max Act: 5.0776. Min Act: -0.1700

Data Index: 576359 (C4 (Web Text))

Max Activating Token Index: 534

Text #17

Max Range: 5.3276. Min Range: -5.3276

Max Act: 5.0776. Min Act: -0.1700

Data Index: 612871 (C4 (Web Text))

Max Activating Token Index: 180

Text #18

Max Range: 5.3276. Min Range: -5.3276

Max Act: 4.9839. Min Act: -0.1700

Data Index: 1264524 (C4 (Web Text))

Max Activating Token Index: 669

Text #19

Max Range: 5.3276. Min Range: -5.3276

Max Act: 5.0776. Min Act: -0.1700

Data Index: 285029 (C4 (Web Text))

Max Activating Token Index: 41