Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2573 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9764. Min Range: -5.9764
Max Act: 5.9764. Min Act: -0.1700
Data Index: 4739561 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9764. Min Range: -5.9764
Max Act: 5.7264. Min Act: -0.1700
Data Index: 2538200 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9764. Min Range: -5.9764
Max Act: 5.6952. Min Act: -0.1700
Data Index: 8089403 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9764. Min Range: -5.9764
Max Act: 5.6014. Min Act: -0.1700
Data Index: 5974195 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9764. Min Range: -5.9764
Max Act: 5.6014. Min Act: -0.1700
Data Index: 2479747 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9764. Min Range: -5.9764
Max Act: 5.5702. Min Act: -0.1700
Data Index: 7618814 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9764. Min Range: -5.9764
Max Act: 5.5702. Min Act: -0.1700
Data Index: 261580 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9764. Min Range: -5.9764
Max Act: 5.5077. Min Act: -0.1700
Data Index: 150114 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9764. Min Range: -5.9764
Max Act: 5.5077. Min Act: -0.1700
Data Index: 6985765 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9764. Min Range: -5.9764
Max Act: 5.5077. Min Act: -0.1700
Data Index: 616518 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9764. Min Range: -5.9764
Max Act: 5.4452. Min Act: -0.1700
Data Index: 4362282 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9764. Min Range: -5.9764
Max Act: 5.4452. Min Act: -0.1700
Data Index: 5508174 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9764. Min Range: -5.9764
Max Act: 5.4139. Min Act: -0.1700
Data Index: 2103067 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9764. Min Range: -5.9764
Max Act: 5.4139. Min Act: -0.1700
Data Index: 2986940 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9764. Min Range: -5.9764
Max Act: 5.4139. Min Act: -0.1700
Data Index: 100433 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9764. Min Range: -5.9764
Max Act: 5.3514. Min Act: -0.1700
Data Index: 1230114 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9764. Min Range: -5.9764
Max Act: 5.3514. Min Act: -0.1700
Data Index: 6789888 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9764. Min Range: -5.9764
Max Act: 5.3202. Min Act: -0.1700
Data Index: 1603620 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9764. Min Range: -5.9764
Max Act: 5.2889. Min Act: -0.1700
Data Index: 5090085 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9764. Min Range: -5.9764
Max Act: 5.2889. Min Act: -0.1700
Data Index: 247970 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #19