Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4619 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0050. Min Range: -7.0050
Max Act: 7.0050. Min Act: -0.1700
Data Index: 7336139 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0050. Min Range: -7.0050
Max Act: 6.9425. Min Act: -0.1700
Data Index: 4777955 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0050. Min Range: -7.0050
Max Act: 6.8488. Min Act: -0.1700
Data Index: 4777954 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0050. Min Range: -7.0050
Max Act: 6.8175. Min Act: -0.1700
Data Index: 8443888 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0050. Min Range: -7.0050
Max Act: 6.7550. Min Act: -0.1700
Data Index: 4255390 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0050. Min Range: -7.0050
Max Act: 6.6925. Min Act: -0.1700
Data Index: 3867478 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0050. Min Range: -7.0050
Max Act: 6.6300. Min Act: -0.1700
Data Index: 7078673 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0050. Min Range: -7.0050
Max Act: 6.5988. Min Act: -0.1700
Data Index: 1895168 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0050. Min Range: -7.0050
Max Act: 6.5988. Min Act: -0.1700
Data Index: 1326269 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0050. Min Range: -7.0050
Max Act: 6.5363. Min Act: -0.1700
Data Index: 1204253 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0050. Min Range: -7.0050
Max Act: 6.5363. Min Act: -0.1700
Data Index: 2299399 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0050. Min Range: -7.0050
Max Act: 6.5363. Min Act: -0.1700
Data Index: 5158930 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0050. Min Range: -7.0050
Max Act: 6.5363. Min Act: -0.1700
Data Index: 6846613 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0050. Min Range: -7.0050
Max Act: 6.5363. Min Act: -0.1700
Data Index: 7113407 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0050. Min Range: -7.0050
Max Act: 6.5363. Min Act: -0.1700
Data Index: 8157974 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0050. Min Range: -7.0050
Max Act: 6.4738. Min Act: -0.1700
Data Index: 1309620 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0050. Min Range: -7.0050
Max Act: 6.4738. Min Act: -0.1700
Data Index: 4325063 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0050. Min Range: -7.0050
Max Act: 6.4425. Min Act: -0.1700
Data Index: 7302091 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0050. Min Range: -7.0050
Max Act: 6.4425. Min Act: -0.1700
Data Index: 7801852 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0050. Min Range: -7.0050
Max Act: 6.4425. Min Act: -0.1700
Data Index: 6568934 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #19