Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3365 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6890. Min Range: -4.6890
Max Act: 4.6890. Min Act: -0.1700
Data Index: 204356 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6890. Min Range: -4.6890
Max Act: 4.5640. Min Act: -0.1700
Data Index: 539371 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6890. Min Range: -4.6890
Max Act: 4.5327. Min Act: -0.1700
Data Index: 4928231 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6890. Min Range: -4.6890
Max Act: 4.5640. Min Act: -0.1700
Data Index: 7006584 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6890. Min Range: -4.6890
Max Act: 4.5327. Min Act: -0.1700
Data Index: 36822 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6890. Min Range: -4.6890
Max Act: 4.5327. Min Act: -0.1700
Data Index: 5145008 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6890. Min Range: -4.6890
Max Act: 4.5327. Min Act: -0.1700
Data Index: 5904158 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6890. Min Range: -4.6890
Max Act: 4.5327. Min Act: -0.1700
Data Index: 3023407 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6890. Min Range: -4.6890
Max Act: 4.5640. Min Act: -0.1700
Data Index: 4406778 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6890. Min Range: -4.6890
Max Act: 4.5015. Min Act: -0.1700
Data Index: 1037179 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6890. Min Range: -4.6890
Max Act: 4.5015. Min Act: -0.1700
Data Index: 7371713 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6890. Min Range: -4.6890
Max Act: 4.5015. Min Act: -0.1700
Data Index: 274512 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6890. Min Range: -4.6890
Max Act: 4.4702. Min Act: -0.1700
Data Index: 4070120 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6890. Min Range: -4.6890
Max Act: 4.4702. Min Act: -0.1700
Data Index: 3850387 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6890. Min Range: -4.6890
Max Act: 4.4390. Min Act: -0.1700
Data Index: 5061891 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6890. Min Range: -4.6890
Max Act: 4.4390. Min Act: -0.1700
Data Index: 1947754 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6890. Min Range: -4.6890
Max Act: 4.3765. Min Act: -0.1700
Data Index: 5729879 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6890. Min Range: -4.6890
Max Act: 4.4077. Min Act: -0.1700
Data Index: 5406669 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6890. Min Range: -4.6890
Max Act: 4.4077. Min Act: -0.1700
Data Index: 7796631 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6890. Min Range: -4.6890
Max Act: 4.4077. Min Act: -0.1700
Data Index: 6697044 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #19