Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3350 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7083. Min Range: -5.7083
Max Act: 5.7083. Min Act: -0.1700
Data Index: 6194206 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7083. Min Range: -5.7083
Max Act: 5.6458. Min Act: -0.1700
Data Index: 2121054 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7083. Min Range: -5.7083
Max Act: 5.5833. Min Act: -0.1700
Data Index: 4359620 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7083. Min Range: -5.7083
Max Act: 5.5520. Min Act: -0.1700
Data Index: 1778 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7083. Min Range: -5.7083
Max Act: 5.5520. Min Act: -0.1700
Data Index: 2935026 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7083. Min Range: -5.7083
Max Act: 5.5520. Min Act: -0.1700
Data Index: 7282144 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7083. Min Range: -5.7083
Max Act: 5.5208. Min Act: -0.1700
Data Index: 6160112 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7083. Min Range: -5.7083
Max Act: 5.4895. Min Act: -0.1700
Data Index: 5153185 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7083. Min Range: -5.7083
Max Act: 5.5208. Min Act: -0.1700
Data Index: 8054396 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7083. Min Range: -5.7083
Max Act: 5.5208. Min Act: -0.1700
Data Index: 7272007 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7083. Min Range: -5.7083
Max Act: 5.4895. Min Act: -0.1700
Data Index: 7737303 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7083. Min Range: -5.7083
Max Act: 5.4583. Min Act: -0.1700
Data Index: 2840994 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7083. Min Range: -5.7083
Max Act: 5.4583. Min Act: -0.1700
Data Index: 6632358 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7083. Min Range: -5.7083
Max Act: 5.4583. Min Act: -0.1700
Data Index: 1397713 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7083. Min Range: -5.7083
Max Act: 5.4270. Min Act: -0.1700
Data Index: 1732377 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7083. Min Range: -5.7083
Max Act: 5.3958. Min Act: -0.1700
Data Index: 5682432 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7083. Min Range: -5.7083
Max Act: 5.3645. Min Act: -0.1700
Data Index: 4664085 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7083. Min Range: -5.7083
Max Act: 5.3645. Min Act: -0.1700
Data Index: 2408564 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7083. Min Range: -5.7083
Max Act: 5.3645. Min Act: -0.1700
Data Index: 5774139 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7083. Min Range: -5.7083
Max Act: 5.3333. Min Act: -0.1700
Data Index: 7550510 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #19