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

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

Neuron 289 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: 3.3002. Min Range: -3.3002

Max Act: 3.3002. Min Act: -0.1700

Data Index: 1169576 (C4 (Web Text))

Max Activating Token Index: 968

Text #1

Max Range: 3.3002. Min Range: -3.3002

Max Act: 3.2531. Min Act: -0.1700

Data Index: 1268689 (C4 (Web Text))

Max Activating Token Index: 790

Text #2

Max Range: 3.3002. Min Range: -3.3002

Max Act: 3.2688. Min Act: -0.1700

Data Index: 1111706 (C4 (Web Text))

Max Activating Token Index: 180

Text #3

Max Range: 3.3002. Min Range: -3.3002

Max Act: 3.2374. Min Act: -0.1700

Data Index: 560117 (C4 (Web Text))

Max Activating Token Index: 652

Text #4

Max Range: 3.3002. Min Range: -3.3002

Max Act: 3.2217. Min Act: -0.1700

Data Index: 344681 (C4 (Web Text))

Max Activating Token Index: 477

Text #5

Max Range: 3.3002. Min Range: -3.3002

Max Act: 3.1745. Min Act: -0.1700

Data Index: 208600 (C4 (Web Text))

Max Activating Token Index: 1003

Text #6

Max Range: 3.3002. Min Range: -3.3002

Max Act: 3.1902. Min Act: -0.1700

Data Index: 196255 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 3.3002. Min Range: -3.3002

Max Act: 3.1902. Min Act: -0.1700

Data Index: 1215369 (C4 (Web Text))

Max Activating Token Index: 675

Text #8

Max Range: 3.3002. Min Range: -3.3002

Max Act: 3.1745. Min Act: -0.1700

Data Index: 376018 (C4 (Web Text))

Max Activating Token Index: 694

Text #9

Max Range: 3.3002. Min Range: -3.3002

Max Act: 3.1587. Min Act: -0.1700

Data Index: 766264 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 3.3002. Min Range: -3.3002

Max Act: 3.1430. Min Act: -0.1700

Data Index: 1654284 (Python Code)

Max Activating Token Index: 378

Text #11

Max Range: 3.3002. Min Range: -3.3002

Max Act: 3.1745. Min Act: -0.1700

Data Index: 509337 (C4 (Web Text))

Max Activating Token Index: 457

Text #12

Max Range: 3.3002. Min Range: -3.3002

Max Act: 3.1745. Min Act: -0.1700

Data Index: 649449 (C4 (Web Text))

Max Activating Token Index: 452

Text #13

Max Range: 3.3002. Min Range: -3.3002

Max Act: 3.1272. Min Act: -0.1700

Data Index: 540804 (C4 (Web Text))

Max Activating Token Index: 634

Text #14

Max Range: 3.3002. Min Range: -3.3002

Max Act: 3.1272. Min Act: -0.1700

Data Index: 260342 (C4 (Web Text))

Max Activating Token Index: 749

Text #15

Max Range: 3.3002. Min Range: -3.3002

Max Act: 3.1115. Min Act: -0.1700

Data Index: 1165762 (C4 (Web Text))

Max Activating Token Index: 413

Text #16

Max Range: 3.3002. Min Range: -3.3002

Max Act: 3.1272. Min Act: -0.1700

Data Index: 768681 (C4 (Web Text))

Max Activating Token Index: 678

Text #17

Max Range: 3.3002. Min Range: -3.3002

Max Act: 3.1272. Min Act: -0.1700

Data Index: 814962 (C4 (Web Text))

Max Activating Token Index: 177

Text #18

Max Range: 3.3002. Min Range: -3.3002

Max Act: 3.0957. Min Act: -0.1700

Data Index: 832729 (C4 (Web Text))

Max Activating Token Index: 940

Text #19

Max Range: 3.3002. Min Range: -3.3002

Max Act: 3.1115. Min Act: -0.1700

Data Index: 430859 (C4 (Web Text))

Max Activating Token Index: 795