Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3463 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.6043. Min Range: -0.6043
Max Act: 0.6043. Min Act: -0.1700
Data Index: 4667966 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.6043. Min Range: -0.6043
Max Act: 0.5965. Min Act: -0.1700
Data Index: 4949101 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.6043. Min Range: -0.6043
Max Act: 0.5808. Min Act: -0.1700
Data Index: 6969044 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.6043. Min Range: -0.6043
Max Act: 0.5886. Min Act: -0.1700
Data Index: 4667965 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.6043. Min Range: -0.6043
Max Act: 0.5268. Min Act: -0.1700
Data Index: 4404957 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.6043. Min Range: -0.6043
Max Act: 0.5268. Min Act: -0.1700
Data Index: 2352932 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.6043. Min Range: -0.6043
Max Act: 0.5192. Min Act: -0.1680
Data Index: 1624465 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.6043. Min Range: -0.6043
Max Act: 0.5116. Min Act: -0.1700
Data Index: 5613087 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.6043. Min Range: -0.6043
Max Act: 0.4817. Min Act: -0.1700
Data Index: 3811392 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.6043. Min Range: -0.6043
Max Act: 0.4742. Min Act: -0.1700
Data Index: 4949106 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.6043. Min Range: -0.6043
Max Act: 0.4742. Min Act: -0.1700
Data Index: 5192774 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.6043. Min Range: -0.6043
Max Act: 0.4742. Min Act: -0.1699
Data Index: 2799638 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.6043. Min Range: -0.6043
Max Act: 0.4742. Min Act: -0.1700
Data Index: 1550457 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.6043. Min Range: -0.6043
Max Act: 0.4669. Min Act: -0.1700
Data Index: 6994913 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.6043. Min Range: -0.6043
Max Act: 0.4742. Min Act: -0.1700
Data Index: 6666921 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.6043. Min Range: -0.6043
Max Act: 0.4595. Min Act: -0.1700
Data Index: 6835968 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.6043. Min Range: -0.6043
Max Act: 0.4522. Min Act: -0.1700
Data Index: 1758838 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.6043. Min Range: -0.6043
Max Act: 0.4522. Min Act: -0.1700
Data Index: 5095894 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.6043. Min Range: -0.6043
Max Act: 0.4449. Min Act: -0.1700
Data Index: 5591721 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.6043. Min Range: -0.6043
Max Act: 0.4449. Min Act: -0.1700
Data Index: 2799636 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #19