Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5621 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9147. Min Range: -5.9147
Max Act: 5.9147. Min Act: -0.1700
Data Index: 1373719 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9147. Min Range: -5.9147
Max Act: 5.6959. Min Act: -0.1700
Data Index: 8104916 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9147. Min Range: -5.9147
Max Act: 5.6959. Min Act: -0.1700
Data Index: 7864485 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9147. Min Range: -5.9147
Max Act: 5.6022. Min Act: -0.1700
Data Index: 8433433 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9147. Min Range: -5.9147
Max Act: 5.5709. Min Act: -0.1700
Data Index: 6746424 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9147. Min Range: -5.9147
Max Act: 5.5709. Min Act: -0.1700
Data Index: 8453480 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9147. Min Range: -5.9147
Max Act: 5.5397. Min Act: -0.1700
Data Index: 6863574 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9147. Min Range: -5.9147
Max Act: 5.5084. Min Act: -0.1700
Data Index: 5262907 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9147. Min Range: -5.9147
Max Act: 5.4772. Min Act: -0.1700
Data Index: 6587506 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9147. Min Range: -5.9147
Max Act: 5.4772. Min Act: -0.1700
Data Index: 1370192 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9147. Min Range: -5.9147
Max Act: 5.5084. Min Act: -0.1700
Data Index: 3490352 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9147. Min Range: -5.9147
Max Act: 5.4459. Min Act: -0.1700
Data Index: 1903805 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9147. Min Range: -5.9147
Max Act: 5.4459. Min Act: -0.1700
Data Index: 1507331 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9147. Min Range: -5.9147
Max Act: 5.4147. Min Act: -0.1700
Data Index: 6655686 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9147. Min Range: -5.9147
Max Act: 5.4147. Min Act: -0.1700
Data Index: 282683 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9147. Min Range: -5.9147
Max Act: 5.4147. Min Act: -0.1700
Data Index: 2133425 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9147. Min Range: -5.9147
Max Act: 5.4147. Min Act: -0.1700
Data Index: 320253 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9147. Min Range: -5.9147
Max Act: 5.3834. Min Act: -0.1700
Data Index: 7302201 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9147. Min Range: -5.9147
Max Act: 5.3834. Min Act: -0.1700
Data Index: 3575673 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9147. Min Range: -5.9147
Max Act: 5.3522. Min Act: -0.1700
Data Index: 1328822 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #19