Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1852 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.5925. Min Range: -3.5925

Max Act: 3.5925. Min Act: -0.1700

Data Index: 644543 (C4 (Web Text))

Max Activating Token Index: 200

Text #1

Max Range: 3.5925. Min Range: -3.5925

Max Act: 3.5925. Min Act: -0.1700

Data Index: 758363 (C4 (Web Text))

Max Activating Token Index: 498

Text #2

Max Range: 3.5925. Min Range: -3.5925

Max Act: 3.5456. Min Act: -0.1700

Data Index: 906290 (C4 (Web Text))

Max Activating Token Index: 154

Text #3

Max Range: 3.5925. Min Range: -3.5925

Max Act: 3.5299. Min Act: -0.1700

Data Index: 1277579 (C4 (Web Text))

Max Activating Token Index: 652

Text #4

Max Range: 3.5925. Min Range: -3.5925

Max Act: 3.5299. Min Act: -0.1700

Data Index: 289934 (C4 (Web Text))

Max Activating Token Index: 269

Text #5

Max Range: 3.5925. Min Range: -3.5925

Max Act: 3.5299. Min Act: -0.1700

Data Index: 151295 (C4 (Web Text))

Max Activating Token Index: 355

Text #6

Max Range: 3.5925. Min Range: -3.5925

Max Act: 3.5142. Min Act: -0.1700

Data Index: 674052 (C4 (Web Text))

Max Activating Token Index: 246

Text #7

Max Range: 3.5925. Min Range: -3.5925

Max Act: 3.5142. Min Act: -0.1700

Data Index: 27695 (C4 (Web Text))

Max Activating Token Index: 466

Text #8

Max Range: 3.5925. Min Range: -3.5925

Max Act: 3.5142. Min Act: -0.1700

Data Index: 161326 (C4 (Web Text))

Max Activating Token Index: 504

Text #9

Max Range: 3.5925. Min Range: -3.5925

Max Act: 3.5142. Min Act: -0.1700

Data Index: 475517 (C4 (Web Text))

Max Activating Token Index: 874

Text #10

Max Range: 3.5925. Min Range: -3.5925

Max Act: 3.5142. Min Act: -0.1700

Data Index: 1070657 (C4 (Web Text))

Max Activating Token Index: 498

Text #11

Max Range: 3.5925. Min Range: -3.5925

Max Act: 3.5142. Min Act: -0.1700

Data Index: 48461 (C4 (Web Text))

Max Activating Token Index: 837

Text #12

Max Range: 3.5925. Min Range: -3.5925

Max Act: 3.5142. Min Act: -0.1700

Data Index: 629013 (C4 (Web Text))

Max Activating Token Index: 265

Text #13

Max Range: 3.5925. Min Range: -3.5925

Max Act: 3.5142. Min Act: -0.1700

Data Index: 1248112 (C4 (Web Text))

Max Activating Token Index: 404

Text #14

Max Range: 3.5925. Min Range: -3.5925

Max Act: 3.5299. Min Act: -0.1700

Data Index: 369608 (C4 (Web Text))

Max Activating Token Index: 748

Text #15

Max Range: 3.5925. Min Range: -3.5925

Max Act: 3.5142. Min Act: -0.1700

Data Index: 619072 (C4 (Web Text))

Max Activating Token Index: 517

Text #16

Max Range: 3.5925. Min Range: -3.5925

Max Act: 3.5142. Min Act: -0.1700

Data Index: 584767 (C4 (Web Text))

Max Activating Token Index: 496

Text #17

Max Range: 3.5925. Min Range: -3.5925

Max Act: 3.4986. Min Act: -0.1700

Data Index: 453000 (C4 (Web Text))

Max Activating Token Index: 799

Text #18

Max Range: 3.5925. Min Range: -3.5925

Max Act: 3.4986. Min Act: -0.1700

Data Index: 24687 (C4 (Web Text))

Max Activating Token Index: 336

Text #19

Max Range: 3.5925. Min Range: -3.5925

Max Act: 3.4986. Min Act: -0.1700

Data Index: 337239 (C4 (Web Text))

Max Activating Token Index: 197