Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3186 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.4812. Min Range: -10.4812
Max Act: 10.4812. Min Act: -0.1700
Data Index: 5777401 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.4812. Min Range: -10.4812
Max Act: 10.4812. Min Act: -0.1700
Data Index: 2734627 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.4812. Min Range: -10.4812
Max Act: 10.4812. Min Act: -0.1700
Data Index: 6627352 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.4812. Min Range: -10.4812
Max Act: 10.3562. Min Act: -0.1700
Data Index: 8147664 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.4812. Min Range: -10.4812
Max Act: 10.3562. Min Act: -0.1700
Data Index: 5096084 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.4812. Min Range: -10.4812
Max Act: 10.2312. Min Act: -0.1700
Data Index: 5436336 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.4812. Min Range: -10.4812
Max Act: 10.1687. Min Act: -0.1700
Data Index: 5794810 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.4812. Min Range: -10.4812
Max Act: 9.9812. Min Act: -0.1700
Data Index: 6400851 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.4812. Min Range: -10.4812
Max Act: 9.9812. Min Act: -0.1700
Data Index: 8273663 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.4812. Min Range: -10.4812
Max Act: 9.9187. Min Act: -0.1700
Data Index: 3485722 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.4812. Min Range: -10.4812
Max Act: 9.9187. Min Act: -0.1700
Data Index: 7334789 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.4812. Min Range: -10.4812
Max Act: 9.8562. Min Act: -0.1700
Data Index: 1888297 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.4812. Min Range: -10.4812
Max Act: 9.7937. Min Act: -0.1700
Data Index: 8152148 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.4812. Min Range: -10.4812
Max Act: 9.8562. Min Act: -0.1700
Data Index: 1712658 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.4812. Min Range: -10.4812
Max Act: 9.8562. Min Act: -0.1700
Data Index: 6194003 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.4812. Min Range: -10.4812
Max Act: 9.8562. Min Act: -0.1700
Data Index: 5794803 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.4812. Min Range: -10.4812
Max Act: 9.8562. Min Act: -0.1700
Data Index: 5777402 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.4812. Min Range: -10.4812
Max Act: 9.7937. Min Act: -0.1700
Data Index: 466324 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.4812. Min Range: -10.4812
Max Act: 9.7312. Min Act: -0.1700
Data Index: 2617395 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.4812. Min Range: -10.4812
Max Act: 9.7937. Min Act: -0.1700
Data Index: 5253311 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #19