Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2691 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3655. Min Range: -5.3655
Max Act: 5.3655. Min Act: -0.1700
Data Index: 8552331 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3655. Min Range: -5.3655
Max Act: 4.5530. Min Act: -0.1700
Data Index: 3247158 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3655. Min Range: -5.3655
Max Act: 4.4905. Min Act: -0.1700
Data Index: 52679 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3655. Min Range: -5.3655
Max Act: 4.4593. Min Act: -0.1700
Data Index: 2056523 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3655. Min Range: -5.3655
Max Act: 4.4593. Min Act: -0.1700
Data Index: 8435150 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3655. Min Range: -5.3655
Max Act: 4.4280. Min Act: -0.1700
Data Index: 6567410 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3655. Min Range: -5.3655
Max Act: 4.4280. Min Act: -0.1700
Data Index: 7716657 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3655. Min Range: -5.3655
Max Act: 4.3968. Min Act: -0.1700
Data Index: 3963136 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3655. Min Range: -5.3655
Max Act: 4.3655. Min Act: -0.1700
Data Index: 5068745 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3655. Min Range: -5.3655
Max Act: 4.3030. Min Act: -0.1700
Data Index: 3167735 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3655. Min Range: -5.3655
Max Act: 4.3030. Min Act: -0.1700
Data Index: 2937159 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3655. Min Range: -5.3655
Max Act: 4.3030. Min Act: -0.1700
Data Index: 4711714 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3655. Min Range: -5.3655
Max Act: 4.3030. Min Act: -0.1700
Data Index: 5833 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3655. Min Range: -5.3655
Max Act: 4.2717. Min Act: -0.1700
Data Index: 1630822 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3655. Min Range: -5.3655
Max Act: 4.3030. Min Act: -0.1700
Data Index: 4056164 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3655. Min Range: -5.3655
Max Act: 4.2405. Min Act: -0.1700
Data Index: 4920564 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3655. Min Range: -5.3655
Max Act: 4.2405. Min Act: -0.1700
Data Index: 220477 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3655. Min Range: -5.3655
Max Act: 4.2405. Min Act: -0.1700
Data Index: 531668 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3655. Min Range: -5.3655
Max Act: 4.2405. Min Act: -0.1700
Data Index: 5943133 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3655. Min Range: -5.3655
Max Act: 4.2405. Min Act: -0.1700
Data Index: 2890034 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #19