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

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

Neuron 677 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: 3.2676. Min Range: -3.2676

Max Act: 3.2519. Min Act: -0.1700

Data Index: 705351 (C4 (Web Text))

Max Activating Token Index: 264

Text #1

Max Range: 3.2676. Min Range: -3.2676

Max Act: 3.2519. Min Act: -0.1700

Data Index: 1318578 (C4 (Web Text))

Max Activating Token Index: 532

Text #2

Max Range: 3.2676. Min Range: -3.2676

Max Act: 3.2519. Min Act: -0.1700

Data Index: 464135 (C4 (Web Text))

Max Activating Token Index: 670

Text #3

Max Range: 3.2676. Min Range: -3.2676

Max Act: 3.2362. Min Act: -0.1700

Data Index: 17178 (C4 (Web Text))

Max Activating Token Index: 732

Text #4

Max Range: 3.2676. Min Range: -3.2676

Max Act: 3.2362. Min Act: -0.1700

Data Index: 1051165 (C4 (Web Text))

Max Activating Token Index: 409

Text #5

Max Range: 3.2676. Min Range: -3.2676

Max Act: 3.2205. Min Act: -0.1700

Data Index: 970586 (C4 (Web Text))

Max Activating Token Index: 970

Text #6

Max Range: 3.2676. Min Range: -3.2676

Max Act: 3.2362. Min Act: -0.1700

Data Index: 53998 (C4 (Web Text))

Max Activating Token Index: 282

Text #7

Max Range: 3.2676. Min Range: -3.2676

Max Act: 3.2205. Min Act: -0.1700

Data Index: 1330412 (C4 (Web Text))

Max Activating Token Index: 891

Text #8

Max Range: 3.2676. Min Range: -3.2676

Max Act: 3.2676. Min Act: -0.1700

Data Index: 883436 (C4 (Web Text))

Max Activating Token Index: 600

Text #9

Max Range: 3.2676. Min Range: -3.2676

Max Act: 3.2047. Min Act: -0.1700

Data Index: 143477 (C4 (Web Text))

Max Activating Token Index: 820

Text #10

Max Range: 3.2676. Min Range: -3.2676

Max Act: 3.2362. Min Act: -0.1700

Data Index: 477094 (C4 (Web Text))

Max Activating Token Index: 250

Text #11

Max Range: 3.2676. Min Range: -3.2676

Max Act: 3.2362. Min Act: -0.1700

Data Index: 74458 (C4 (Web Text))

Max Activating Token Index: 814

Text #12

Max Range: 3.2676. Min Range: -3.2676

Max Act: 3.2205. Min Act: -0.1700

Data Index: 926917 (C4 (Web Text))

Max Activating Token Index: 884

Text #13

Max Range: 3.2676. Min Range: -3.2676

Max Act: 3.2047. Min Act: -0.1700

Data Index: 535381 (C4 (Web Text))

Max Activating Token Index: 869

Text #14

Max Range: 3.2676. Min Range: -3.2676

Max Act: 3.2047. Min Act: -0.1700

Data Index: 236377 (C4 (Web Text))

Max Activating Token Index: 577

Text #15

Max Range: 3.2676. Min Range: -3.2676

Max Act: 3.1890. Min Act: -0.1700

Data Index: 374950 (C4 (Web Text))

Max Activating Token Index: 1002

Text #16

Max Range: 3.2676. Min Range: -3.2676

Max Act: 3.2362. Min Act: -0.1700

Data Index: 815816 (C4 (Web Text))

Max Activating Token Index: 632

Text #17

Max Range: 3.2676. Min Range: -3.2676

Max Act: 3.1733. Min Act: -0.1700

Data Index: 77328 (C4 (Web Text))

Max Activating Token Index: 359

Text #18

Max Range: 3.2676. Min Range: -3.2676

Max Act: 3.1890. Min Act: -0.1700

Data Index: 983327 (C4 (Web Text))

Max Activating Token Index: 758

Text #19

Max Range: 3.2676. Min Range: -3.2676

Max Act: 3.2205. Min Act: -0.1700

Data Index: 339416 (C4 (Web Text))

Max Activating Token Index: 573