Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4471 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1761. Min Range: -6.1761
Max Act: 6.1761. Min Act: -0.1700
Data Index: 7415712 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1761. Min Range: -6.1761
Max Act: 5.9886. Min Act: -0.1700
Data Index: 7376389 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1761. Min Range: -6.1761
Max Act: 5.8948. Min Act: -0.1700
Data Index: 3861150 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1761. Min Range: -6.1761
Max Act: 5.9261. Min Act: -0.1700
Data Index: 4137882 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1761. Min Range: -6.1761
Max Act: 5.9261. Min Act: -0.1700
Data Index: 6616837 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1761. Min Range: -6.1761
Max Act: 5.8948. Min Act: -0.1700
Data Index: 1209888 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1761. Min Range: -6.1761
Max Act: 5.8948. Min Act: -0.1700
Data Index: 4933812 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1761. Min Range: -6.1761
Max Act: 5.8948. Min Act: -0.1700
Data Index: 7366024 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1761. Min Range: -6.1761
Max Act: 5.8323. Min Act: -0.1700
Data Index: 6528922 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1761. Min Range: -6.1761
Max Act: 5.8323. Min Act: -0.1700
Data Index: 3487710 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1761. Min Range: -6.1761
Max Act: 5.8323. Min Act: -0.1700
Data Index: 1004440 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1761. Min Range: -6.1761
Max Act: 5.8323. Min Act: -0.1700
Data Index: 4892056 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1761. Min Range: -6.1761
Max Act: 5.8323. Min Act: -0.1700
Data Index: 1262 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1761. Min Range: -6.1761
Max Act: 5.8011. Min Act: -0.1700
Data Index: 1553663 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1761. Min Range: -6.1761
Max Act: 5.8011. Min Act: -0.1700
Data Index: 296948 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1761. Min Range: -6.1761
Max Act: 5.8011. Min Act: -0.1700
Data Index: 7290797 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1761. Min Range: -6.1761
Max Act: 5.8011. Min Act: -0.1700
Data Index: 5562770 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1761. Min Range: -6.1761
Max Act: 5.7698. Min Act: -0.1700
Data Index: 6997208 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1761. Min Range: -6.1761
Max Act: 5.8011. Min Act: -0.1700
Data Index: 4124821 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1761. Min Range: -6.1761
Max Act: 5.7698. Min Act: -0.1700
Data Index: 1401077 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #19