Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3689 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5077. Min Range: -9.5077
Max Act: 9.4452. Min Act: -0.1700
Data Index: 5729876 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5077. Min Range: -9.5077
Max Act: 9.5077. Min Act: -0.1700
Data Index: 2258098 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5077. Min Range: -9.5077
Max Act: 9.3827. Min Act: -0.1700
Data Index: 6904645 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5077. Min Range: -9.5077
Max Act: 9.3827. Min Act: -0.1700
Data Index: 2195220 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5077. Min Range: -9.5077
Max Act: 9.3827. Min Act: -0.1700
Data Index: 1101412 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5077. Min Range: -9.5077
Max Act: 9.3827. Min Act: -0.1700
Data Index: 2249586 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5077. Min Range: -9.5077
Max Act: 9.3827. Min Act: -0.1700
Data Index: 230349 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5077. Min Range: -9.5077
Max Act: 9.3202. Min Act: -0.1700
Data Index: 430380 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5077. Min Range: -9.5077
Max Act: 9.3202. Min Act: -0.1700
Data Index: 8003457 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5077. Min Range: -9.5077
Max Act: 9.3202. Min Act: -0.1700
Data Index: 1780753 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5077. Min Range: -9.5077
Max Act: 9.2577. Min Act: -0.1700
Data Index: 4816165 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5077. Min Range: -9.5077
Max Act: 9.2577. Min Act: -0.1700
Data Index: 7070245 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5077. Min Range: -9.5077
Max Act: 9.2577. Min Act: -0.1700
Data Index: 4793969 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5077. Min Range: -9.5077
Max Act: 9.2577. Min Act: -0.1700
Data Index: 4146060 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5077. Min Range: -9.5077
Max Act: 9.3202. Min Act: -0.1700
Data Index: 6792881 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5077. Min Range: -9.5077
Max Act: 9.1952. Min Act: -0.1700
Data Index: 5801653 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5077. Min Range: -9.5077
Max Act: 9.1952. Min Act: -0.1700
Data Index: 4289409 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5077. Min Range: -9.5077
Max Act: 9.1952. Min Act: -0.1700
Data Index: 7745082 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5077. Min Range: -9.5077
Max Act: 9.1952. Min Act: -0.1700
Data Index: 6003755 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5077. Min Range: -9.5077
Max Act: 9.1952. Min Act: -0.1700
Data Index: 8081102 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #19