Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3420 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.6588. Min Range: -11.6588
Max Act: 11.6588. Min Act: -0.1700
Data Index: 3053228 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.6588. Min Range: -11.6588
Max Act: 11.5338. Min Act: -0.1700
Data Index: 7328266 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.6588. Min Range: -11.6588
Max Act: 11.5338. Min Act: -0.1700
Data Index: 6776691 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.6588. Min Range: -11.6588
Max Act: 11.2838. Min Act: -0.1700
Data Index: 4655051 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.6588. Min Range: -11.6588
Max Act: 11.1588. Min Act: -0.1700
Data Index: 231157 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.6588. Min Range: -11.6588
Max Act: 11.1588. Min Act: -0.1700
Data Index: 1689818 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.6588. Min Range: -11.6588
Max Act: 11.0963. Min Act: -0.1700
Data Index: 7126276 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.6588. Min Range: -11.6588
Max Act: 10.9088. Min Act: -0.1700
Data Index: 2231008 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.6588. Min Range: -11.6588
Max Act: 10.9088. Min Act: -0.1700
Data Index: 8072627 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.6588. Min Range: -11.6588
Max Act: 10.9088. Min Act: -0.1700
Data Index: 6263514 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.6588. Min Range: -11.6588
Max Act: 10.8463. Min Act: -0.1700
Data Index: 2194043 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.6588. Min Range: -11.6588
Max Act: 10.8463. Min Act: -0.1700
Data Index: 1381949 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.6588. Min Range: -11.6588
Max Act: 10.8463. Min Act: -0.1700
Data Index: 8547564 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.6588. Min Range: -11.6588
Max Act: 10.7838. Min Act: -0.1700
Data Index: 710734 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.6588. Min Range: -11.6588
Max Act: 10.9088. Min Act: -0.1700
Data Index: 1349073 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.6588. Min Range: -11.6588
Max Act: 10.8463. Min Act: -0.1700
Data Index: 7883192 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.6588. Min Range: -11.6588
Max Act: 10.8463. Min Act: -0.1700
Data Index: 2956574 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.6588. Min Range: -11.6588
Max Act: 10.7838. Min Act: -0.1700
Data Index: 4823763 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.6588. Min Range: -11.6588
Max Act: 10.7838. Min Act: -0.1700
Data Index: 7644296 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.6588. Min Range: -11.6588
Max Act: 10.7213. Min Act: -0.1700
Data Index: 1289192 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #19