Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4493 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2620. Min Range: -7.2620
Max Act: 7.2620. Min Act: -0.1700
Data Index: 8437627 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2620. Min Range: -7.2620
Max Act: 6.9495. Min Act: -0.1700
Data Index: 7555305 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2620. Min Range: -7.2620
Max Act: 6.8870. Min Act: -0.1700
Data Index: 4139822 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2620. Min Range: -7.2620
Max Act: 6.8245. Min Act: -0.1700
Data Index: 2991558 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2620. Min Range: -7.2620
Max Act: 6.8245. Min Act: -0.1700
Data Index: 55402 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2620. Min Range: -7.2620
Max Act: 6.8557. Min Act: -0.1700
Data Index: 1189928 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2620. Min Range: -7.2620
Max Act: 6.7932. Min Act: -0.1700
Data Index: 8516873 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2620. Min Range: -7.2620
Max Act: 6.7932. Min Act: -0.1700
Data Index: 2518466 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2620. Min Range: -7.2620
Max Act: 6.7620. Min Act: -0.1700
Data Index: 5994656 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2620. Min Range: -7.2620
Max Act: 6.7620. Min Act: -0.1700
Data Index: 4326016 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2620. Min Range: -7.2620
Max Act: 6.7307. Min Act: -0.1700
Data Index: 7615233 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2620. Min Range: -7.2620
Max Act: 6.7307. Min Act: -0.1700
Data Index: 977598 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2620. Min Range: -7.2620
Max Act: 6.7307. Min Act: -0.1700
Data Index: 72325 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2620. Min Range: -7.2620
Max Act: 6.6995. Min Act: -0.1700
Data Index: 7485883 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2620. Min Range: -7.2620
Max Act: 6.6995. Min Act: -0.1700
Data Index: 2053962 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2620. Min Range: -7.2620
Max Act: 6.6995. Min Act: -0.1700
Data Index: 8332613 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2620. Min Range: -7.2620
Max Act: 6.6370. Min Act: -0.1700
Data Index: 4356421 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2620. Min Range: -7.2620
Max Act: 6.6370. Min Act: -0.1700
Data Index: 2562238 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2620. Min Range: -7.2620
Max Act: 6.6057. Min Act: -0.1700
Data Index: 2127625 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2620. Min Range: -7.2620
Max Act: 6.6057. Min Act: -0.1700
Data Index: 7901587 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #19