Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3880 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7026. Min Range: -9.7026
Max Act: 9.7026. Min Act: -0.1700
Data Index: 6341219 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7026. Min Range: -9.7026
Max Act: 9.2651. Min Act: -0.1700
Data Index: 4678827 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7026. Min Range: -9.7026
Max Act: 9.3276. Min Act: -0.1700
Data Index: 5884866 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7026. Min Range: -9.7026
Max Act: 9.0151. Min Act: -0.1700
Data Index: 8361037 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7026. Min Range: -9.7026
Max Act: 8.8901. Min Act: -0.1700
Data Index: 2065268 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7026. Min Range: -9.7026
Max Act: 8.8276. Min Act: -0.1700
Data Index: 2230541 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7026. Min Range: -9.7026
Max Act: 8.7651. Min Act: -0.1700
Data Index: 3266448 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7026. Min Range: -9.7026
Max Act: 8.7651. Min Act: -0.1700
Data Index: 1195467 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7026. Min Range: -9.7026
Max Act: 8.7651. Min Act: -0.1700
Data Index: 2695658 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7026. Min Range: -9.7026
Max Act: 8.7651. Min Act: -0.1700
Data Index: 6423712 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7026. Min Range: -9.7026
Max Act: 8.7026. Min Act: -0.1700
Data Index: 7999138 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7026. Min Range: -9.7026
Max Act: 8.7026. Min Act: -0.1700
Data Index: 5442591 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7026. Min Range: -9.7026
Max Act: 8.7026. Min Act: -0.1700
Data Index: 1608284 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7026. Min Range: -9.7026
Max Act: 8.7026. Min Act: -0.1700
Data Index: 7824059 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7026. Min Range: -9.7026
Max Act: 8.6401. Min Act: -0.1700
Data Index: 8117442 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7026. Min Range: -9.7026
Max Act: 8.6401. Min Act: -0.1700
Data Index: 2347295 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7026. Min Range: -9.7026
Max Act: 8.5776. Min Act: -0.1700
Data Index: 8484425 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7026. Min Range: -9.7026
Max Act: 8.6401. Min Act: -0.1700
Data Index: 4282707 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7026. Min Range: -9.7026
Max Act: 8.6401. Min Act: -0.1700
Data Index: 2038741 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7026. Min Range: -9.7026
Max Act: 8.5776. Min Act: -0.1700
Data Index: 2886480 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #19