Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 590 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9653. Min Range: -5.9653
Max Act: 5.9653. Min Act: -0.1700
Data Index: 543372 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9653. Min Range: -5.9653
Max Act: 5.9653. Min Act: -0.1700
Data Index: 8538574 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9653. Min Range: -5.9653
Max Act: 5.8090. Min Act: -0.1700
Data Index: 8534640 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9653. Min Range: -5.9653
Max Act: 5.8403. Min Act: -0.1700
Data Index: 2057240 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9653. Min Range: -5.9653
Max Act: 5.7778. Min Act: -0.1700
Data Index: 7347371 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9653. Min Range: -5.9653
Max Act: 5.7778. Min Act: -0.1700
Data Index: 6080792 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9653. Min Range: -5.9653
Max Act: 5.7778. Min Act: -0.1700
Data Index: 949725 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9653. Min Range: -5.9653
Max Act: 5.7778. Min Act: -0.1700
Data Index: 1294110 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9653. Min Range: -5.9653
Max Act: 5.7465. Min Act: -0.1700
Data Index: 480050 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9653. Min Range: -5.9653
Max Act: 5.6840. Min Act: -0.1700
Data Index: 1624115 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9653. Min Range: -5.9653
Max Act: 5.7153. Min Act: -0.1700
Data Index: 4546676 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9653. Min Range: -5.9653
Max Act: 5.7153. Min Act: -0.1700
Data Index: 7057862 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9653. Min Range: -5.9653
Max Act: 5.6840. Min Act: -0.1700
Data Index: 4596813 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9653. Min Range: -5.9653
Max Act: 5.6528. Min Act: -0.1700
Data Index: 1857242 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9653. Min Range: -5.9653
Max Act: 5.7153. Min Act: -0.1700
Data Index: 385787 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9653. Min Range: -5.9653
Max Act: 5.6840. Min Act: -0.1700
Data Index: 6302754 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9653. Min Range: -5.9653
Max Act: 5.6528. Min Act: -0.1700
Data Index: 4492441 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9653. Min Range: -5.9653
Max Act: 5.6528. Min Act: -0.1700
Data Index: 7619095 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9653. Min Range: -5.9653
Max Act: 5.6215. Min Act: -0.1700
Data Index: 769796 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9653. Min Range: -5.9653
Max Act: 5.6528. Min Act: -0.1700
Data Index: 813917 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #19