Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2308 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8011. Min Range: -5.8011
Max Act: 5.8011. Min Act: -0.1700
Data Index: 4595261 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8011. Min Range: -5.8011
Max Act: 5.2073. Min Act: -0.1700
Data Index: 5121030 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8011. Min Range: -5.8011
Max Act: 5.2386. Min Act: -0.1700
Data Index: 8192436 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8011. Min Range: -5.8011
Max Act: 5.1448. Min Act: -0.1700
Data Index: 6777670 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8011. Min Range: -5.8011
Max Act: 5.1448. Min Act: -0.1700
Data Index: 851592 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8011. Min Range: -5.8011
Max Act: 5.0823. Min Act: -0.1700
Data Index: 6049567 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8011. Min Range: -5.8011
Max Act: 5.0511. Min Act: -0.1700
Data Index: 3495418 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8011. Min Range: -5.8011
Max Act: 5.0511. Min Act: -0.1700
Data Index: 4489486 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8011. Min Range: -5.8011
Max Act: 5.0511. Min Act: -0.1700
Data Index: 4902686 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8011. Min Range: -5.8011
Max Act: 5.0198. Min Act: -0.1700
Data Index: 4507213 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8011. Min Range: -5.8011
Max Act: 5.0198. Min Act: -0.1700
Data Index: 7735442 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8011. Min Range: -5.8011
Max Act: 5.0198. Min Act: -0.1700
Data Index: 7828629 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8011. Min Range: -5.8011
Max Act: 4.9886. Min Act: -0.1700
Data Index: 7600293 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8011. Min Range: -5.8011
Max Act: 4.9886. Min Act: -0.1700
Data Index: 3671901 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8011. Min Range: -5.8011
Max Act: 4.9573. Min Act: -0.1700
Data Index: 6592488 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8011. Min Range: -5.8011
Max Act: 4.9573. Min Act: -0.1700
Data Index: 4655892 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8011. Min Range: -5.8011
Max Act: 4.9573. Min Act: -0.1700
Data Index: 2329571 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8011. Min Range: -5.8011
Max Act: 4.9573. Min Act: -0.1700
Data Index: 572763 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8011. Min Range: -5.8011
Max Act: 4.9573. Min Act: -0.1700
Data Index: 7472580 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8011. Min Range: -5.8011
Max Act: 4.9573. Min Act: -0.1700
Data Index: 1114032 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #19