Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2271 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7050. Min Range: -8.7050
Max Act: 8.7050. Min Act: -0.1700
Data Index: 425784 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7050. Min Range: -8.7050
Max Act: 8.5800. Min Act: -0.1700
Data Index: 5178153 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7050. Min Range: -8.7050
Max Act: 8.5175. Min Act: -0.1700
Data Index: 6216200 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7050. Min Range: -8.7050
Max Act: 8.4550. Min Act: -0.1700
Data Index: 8831595 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7050. Min Range: -8.7050
Max Act: 8.3300. Min Act: -0.1700
Data Index: 3093807 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7050. Min Range: -8.7050
Max Act: 8.3300. Min Act: -0.1700
Data Index: 3156522 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7050. Min Range: -8.7050
Max Act: 8.2050. Min Act: -0.1700
Data Index: 3700459 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7050. Min Range: -8.7050
Max Act: 8.2050. Min Act: -0.1700
Data Index: 5749009 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7050. Min Range: -8.7050
Max Act: 8.1425. Min Act: -0.1700
Data Index: 741066 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7050. Min Range: -8.7050
Max Act: 8.1425. Min Act: -0.1700
Data Index: 3786957 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7050. Min Range: -8.7050
Max Act: 8.1425. Min Act: -0.1700
Data Index: 606089 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7050. Min Range: -8.7050
Max Act: 8.0175. Min Act: -0.1700
Data Index: 3686888 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7050. Min Range: -8.7050
Max Act: 8.0800. Min Act: -0.1700
Data Index: 6515009 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7050. Min Range: -8.7050
Max Act: 8.0800. Min Act: -0.1700
Data Index: 6412971 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7050. Min Range: -8.7050
Max Act: 8.0175. Min Act: -0.1700
Data Index: 5807321 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7050. Min Range: -8.7050
Max Act: 8.0175. Min Act: -0.1700
Data Index: 4660665 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7050. Min Range: -8.7050
Max Act: 8.0175. Min Act: -0.1700
Data Index: 4130447 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7050. Min Range: -8.7050
Max Act: 8.0175. Min Act: -0.1700
Data Index: 209928 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7050. Min Range: -8.7050
Max Act: 8.0175. Min Act: -0.1700
Data Index: 2693389 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7050. Min Range: -8.7050
Max Act: 8.0175. Min Act: -0.1700
Data Index: 7110290 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #19