Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3508 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6831. Min Range: -4.6831
Max Act: 4.6831. Min Act: -0.1700
Data Index: 5283222 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6831. Min Range: -4.6831
Max Act: 4.4956. Min Act: -0.1700
Data Index: 2700245 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6831. Min Range: -4.6831
Max Act: 4.4956. Min Act: -0.1700
Data Index: 7097902 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6831. Min Range: -4.6831
Max Act: 4.4956. Min Act: -0.1700
Data Index: 4367288 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6831. Min Range: -4.6831
Max Act: 4.4644. Min Act: -0.1700
Data Index: 3598802 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6831. Min Range: -4.6831
Max Act: 4.4331. Min Act: -0.1700
Data Index: 4885359 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6831. Min Range: -4.6831
Max Act: 4.4644. Min Act: -0.1700
Data Index: 8829560 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6831. Min Range: -4.6831
Max Act: 4.4644. Min Act: -0.1700
Data Index: 377428 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6831. Min Range: -4.6831
Max Act: 4.4644. Min Act: -0.1700
Data Index: 7456051 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6831. Min Range: -4.6831
Max Act: 4.4331. Min Act: -0.1700
Data Index: 671970 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6831. Min Range: -4.6831
Max Act: 4.4331. Min Act: -0.1700
Data Index: 8457277 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6831. Min Range: -4.6831
Max Act: 4.4331. Min Act: -0.1700
Data Index: 4672648 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6831. Min Range: -4.6831
Max Act: 4.4331. Min Act: -0.1700
Data Index: 5483270 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6831. Min Range: -4.6831
Max Act: 4.4331. Min Act: -0.1700
Data Index: 913095 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6831. Min Range: -4.6831
Max Act: 4.4644. Min Act: -0.1700
Data Index: 2842008 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6831. Min Range: -4.6831
Max Act: 4.4331. Min Act: -0.1700
Data Index: 5404845 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6831. Min Range: -4.6831
Max Act: 4.4019. Min Act: -0.1700
Data Index: 3365802 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6831. Min Range: -4.6831
Max Act: 4.4331. Min Act: -0.1700
Data Index: 6383287 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6831. Min Range: -4.6831
Max Act: 4.4019. Min Act: -0.1700
Data Index: 5954858 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6831. Min Range: -4.6831
Max Act: 4.4331. Min Act: -0.1700
Data Index: 4534278 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #19