Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2756 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1100. Min Range: -5.1100
Max Act: 5.0788. Min Act: -0.1700
Data Index: 3374213 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1100. Min Range: -5.1100
Max Act: 5.1100. Min Act: -0.1700
Data Index: 8184941 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1100. Min Range: -5.1100
Max Act: 5.0475. Min Act: -0.1700
Data Index: 5187128 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1100. Min Range: -5.1100
Max Act: 5.0475. Min Act: -0.1700
Data Index: 911090 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1100. Min Range: -5.1100
Max Act: 4.9538. Min Act: -0.1700
Data Index: 4900249 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1100. Min Range: -5.1100
Max Act: 4.9225. Min Act: -0.1700
Data Index: 3781128 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1100. Min Range: -5.1100
Max Act: 4.8913. Min Act: -0.1700
Data Index: 4670188 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1100. Min Range: -5.1100
Max Act: 4.8913. Min Act: -0.1700
Data Index: 6117414 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1100. Min Range: -5.1100
Max Act: 4.8600. Min Act: -0.1700
Data Index: 8401713 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1100. Min Range: -5.1100
Max Act: 4.8288. Min Act: -0.1700
Data Index: 5954046 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1100. Min Range: -5.1100
Max Act: 4.8288. Min Act: -0.1700
Data Index: 2299744 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1100. Min Range: -5.1100
Max Act: 4.8600. Min Act: -0.1700
Data Index: 7556501 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1100. Min Range: -5.1100
Max Act: 4.8288. Min Act: -0.1700
Data Index: 4796144 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1100. Min Range: -5.1100
Max Act: 4.7975. Min Act: -0.1700
Data Index: 2041210 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1100. Min Range: -5.1100
Max Act: 4.8288. Min Act: -0.1700
Data Index: 8170923 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1100. Min Range: -5.1100
Max Act: 4.7975. Min Act: -0.1700
Data Index: 2641963 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1100. Min Range: -5.1100
Max Act: 4.7662. Min Act: -0.1700
Data Index: 335215 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1100. Min Range: -5.1100
Max Act: 4.7662. Min Act: -0.1700
Data Index: 2814450 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1100. Min Range: -5.1100
Max Act: 4.7350. Min Act: -0.1700
Data Index: 4821281 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1100. Min Range: -5.1100
Max Act: 4.7350. Min Act: -0.1700
Data Index: 924502 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #19