Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5368 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7953. Min Range: -5.7953
Max Act: 5.7953. Min Act: -0.1700
Data Index: 2706399 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7953. Min Range: -5.7953
Max Act: 5.5141. Min Act: -0.1700
Data Index: 8598519 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7953. Min Range: -5.7953
Max Act: 5.3266. Min Act: -0.1700
Data Index: 806658 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7953. Min Range: -5.7953
Max Act: 5.3578. Min Act: -0.1700
Data Index: 7781477 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7953. Min Range: -5.7953
Max Act: 5.3578. Min Act: -0.1700
Data Index: 4605486 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7953. Min Range: -5.7953
Max Act: 5.2953. Min Act: -0.1700
Data Index: 2714085 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7953. Min Range: -5.7953
Max Act: 5.2953. Min Act: -0.1700
Data Index: 8779613 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7953. Min Range: -5.7953
Max Act: 5.2953. Min Act: -0.1700
Data Index: 1663312 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7953. Min Range: -5.7953
Max Act: 5.2953. Min Act: -0.1700
Data Index: 4559715 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7953. Min Range: -5.7953
Max Act: 5.2641. Min Act: -0.1700
Data Index: 8550789 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7953. Min Range: -5.7953
Max Act: 5.2641. Min Act: -0.1700
Data Index: 8768012 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7953. Min Range: -5.7953
Max Act: 5.2641. Min Act: -0.1700
Data Index: 3038666 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7953. Min Range: -5.7953
Max Act: 5.2641. Min Act: -0.1700
Data Index: 5837406 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7953. Min Range: -5.7953
Max Act: 5.2641. Min Act: -0.1700
Data Index: 5879310 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7953. Min Range: -5.7953
Max Act: 5.2641. Min Act: -0.1700
Data Index: 1034622 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7953. Min Range: -5.7953
Max Act: 5.2328. Min Act: -0.1700
Data Index: 4860600 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7953. Min Range: -5.7953
Max Act: 5.2016. Min Act: -0.1700
Data Index: 2799141 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7953. Min Range: -5.7953
Max Act: 5.2328. Min Act: -0.1700
Data Index: 7175065 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7953. Min Range: -5.7953
Max Act: 5.2016. Min Act: -0.1700
Data Index: 8784847 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7953. Min Range: -5.7953
Max Act: 5.2016. Min Act: -0.1700
Data Index: 7847958 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #19