Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4003 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8011. Min Range: -8.8011
Max Act: 8.8011. Min Act: -0.1700
Data Index: 5084713 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8011. Min Range: -8.8011
Max Act: 8.4886. Min Act: -0.1700
Data Index: 288985 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8011. Min Range: -8.8011
Max Act: 8.4261. Min Act: -0.1700
Data Index: 2775618 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8011. Min Range: -8.8011
Max Act: 8.3636. Min Act: -0.1700
Data Index: 3489448 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8011. Min Range: -8.8011
Max Act: 8.3636. Min Act: -0.1700
Data Index: 1571822 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8011. Min Range: -8.8011
Max Act: 8.3011. Min Act: -0.1700
Data Index: 5971557 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8011. Min Range: -8.8011
Max Act: 8.3011. Min Act: -0.1700
Data Index: 7105346 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8011. Min Range: -8.8011
Max Act: 8.2386. Min Act: -0.1700
Data Index: 3481418 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8011. Min Range: -8.8011
Max Act: 8.2386. Min Act: -0.1700
Data Index: 4353259 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8011. Min Range: -8.8011
Max Act: 8.2386. Min Act: -0.1700
Data Index: 61072 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8011. Min Range: -8.8011
Max Act: 8.1761. Min Act: -0.1700
Data Index: 1040996 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8011. Min Range: -8.8011
Max Act: 8.1761. Min Act: -0.1700
Data Index: 491923 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8011. Min Range: -8.8011
Max Act: 8.1136. Min Act: -0.1700
Data Index: 538 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8011. Min Range: -8.8011
Max Act: 8.1761. Min Act: -0.1700
Data Index: 6756389 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8011. Min Range: -8.8011
Max Act: 8.1761. Min Act: -0.1700
Data Index: 14951 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8011. Min Range: -8.8011
Max Act: 8.1761. Min Act: -0.1700
Data Index: 1139368 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8011. Min Range: -8.8011
Max Act: 8.1136. Min Act: -0.1700
Data Index: 4889701 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8011. Min Range: -8.8011
Max Act: 8.1136. Min Act: -0.1700
Data Index: 1051825 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8011. Min Range: -8.8011
Max Act: 8.0511. Min Act: -0.1700
Data Index: 1004850 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8011. Min Range: -8.8011
Max Act: 8.1136. Min Act: -0.1700
Data Index: 3239659 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #19