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

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

Neuron 1424 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1177. Min Range: -5.1177

Max Act: 5.0865. Min Act: -0.1700

Data Index: 1078462 (C4 (Web Text))

Max Activating Token Index: 889

Text #1

Max Range: 5.1177. Min Range: -5.1177

Max Act: 5.0239. Min Act: -0.1700

Data Index: 2474 (C4 (Web Text))

Max Activating Token Index: 833

Text #2

Max Range: 5.1177. Min Range: -5.1177

Max Act: 5.0239. Min Act: -0.1700

Data Index: 162408 (C4 (Web Text))

Max Activating Token Index: 967

Text #3

Max Range: 5.1177. Min Range: -5.1177

Max Act: 5.0865. Min Act: -0.1700

Data Index: 533859 (C4 (Web Text))

Max Activating Token Index: 680

Text #4

Max Range: 5.1177. Min Range: -5.1177

Max Act: 5.0552. Min Act: -0.1700

Data Index: 940889 (C4 (Web Text))

Max Activating Token Index: 897

Text #5

Max Range: 5.1177. Min Range: -5.1177

Max Act: 4.9927. Min Act: -0.1700

Data Index: 187604 (C4 (Web Text))

Max Activating Token Index: 937

Text #6

Max Range: 5.1177. Min Range: -5.1177

Max Act: 5.1177. Min Act: -0.1700

Data Index: 856151 (C4 (Web Text))

Max Activating Token Index: 942

Text #7

Max Range: 5.1177. Min Range: -5.1177

Max Act: 5.0865. Min Act: -0.1700

Data Index: 981182 (C4 (Web Text))

Max Activating Token Index: 904

Text #8

Max Range: 5.1177. Min Range: -5.1177

Max Act: 4.9614. Min Act: -0.1700

Data Index: 737691 (C4 (Web Text))

Max Activating Token Index: 915

Text #9

Max Range: 5.1177. Min Range: -5.1177

Max Act: 5.0239. Min Act: -0.1700

Data Index: 657941 (C4 (Web Text))

Max Activating Token Index: 918

Text #10

Max Range: 5.1177. Min Range: -5.1177

Max Act: 4.9614. Min Act: -0.1700

Data Index: 937669 (C4 (Web Text))

Max Activating Token Index: 907

Text #11

Max Range: 5.1177. Min Range: -5.1177

Max Act: 4.9614. Min Act: -0.1700

Data Index: 1338149 (C4 (Web Text))

Max Activating Token Index: 387

Text #12

Max Range: 5.1177. Min Range: -5.1177

Max Act: 5.0239. Min Act: -0.1700

Data Index: 28935 (C4 (Web Text))

Max Activating Token Index: 797

Text #13

Max Range: 5.1177. Min Range: -5.1177

Max Act: 4.9927. Min Act: -0.1700

Data Index: 209375 (C4 (Web Text))

Max Activating Token Index: 389

Text #14

Max Range: 5.1177. Min Range: -5.1177

Max Act: 4.8989. Min Act: -0.1700

Data Index: 285213 (C4 (Web Text))

Max Activating Token Index: 473

Text #15

Max Range: 5.1177. Min Range: -5.1177

Max Act: 4.9614. Min Act: -0.1700

Data Index: 1075911 (C4 (Web Text))

Max Activating Token Index: 397

Text #16

Max Range: 5.1177. Min Range: -5.1177

Max Act: 4.8364. Min Act: -0.1700

Data Index: 1207215 (C4 (Web Text))

Max Activating Token Index: 705

Text #17

Max Range: 5.1177. Min Range: -5.1177

Max Act: 4.8677. Min Act: -0.1700

Data Index: 864641 (C4 (Web Text))

Max Activating Token Index: 361

Text #18

Max Range: 5.1177. Min Range: -5.1177

Max Act: 4.9302. Min Act: -0.1700

Data Index: 679042 (C4 (Web Text))

Max Activating Token Index: 445

Text #19

Max Range: 5.1177. Min Range: -5.1177

Max Act: 4.8989. Min Act: -0.1700

Data Index: 137676 (C4 (Web Text))

Max Activating Token Index: 413