Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3938 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3071. Min Range: -6.3071
Max Act: 6.3071. Min Act: -0.1700
Data Index: 4548678 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3071. Min Range: -6.3071
Max Act: 6.2446. Min Act: -0.1700
Data Index: 6619798 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3071. Min Range: -6.3071
Max Act: 6.0883. Min Act: -0.1700
Data Index: 1291630 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3071. Min Range: -6.3071
Max Act: 6.0883. Min Act: -0.1700
Data Index: 6109978 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3071. Min Range: -6.3071
Max Act: 6.0571. Min Act: -0.1700
Data Index: 380172 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3071. Min Range: -6.3071
Max Act: 6.0258. Min Act: -0.1700
Data Index: 4617311 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3071. Min Range: -6.3071
Max Act: 6.0258. Min Act: -0.1700
Data Index: 117229 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3071. Min Range: -6.3071
Max Act: 6.0258. Min Act: -0.1700
Data Index: 1141166 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3071. Min Range: -6.3071
Max Act: 5.9946. Min Act: -0.1700
Data Index: 7776997 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3071. Min Range: -6.3071
Max Act: 5.9946. Min Act: -0.1700
Data Index: 2068382 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3071. Min Range: -6.3071
Max Act: 5.9633. Min Act: -0.1700
Data Index: 2468774 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3071. Min Range: -6.3071
Max Act: 5.9633. Min Act: -0.1700
Data Index: 4337555 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3071. Min Range: -6.3071
Max Act: 5.9633. Min Act: -0.1700
Data Index: 6028227 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3071. Min Range: -6.3071
Max Act: 5.9633. Min Act: -0.1700
Data Index: 5872525 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3071. Min Range: -6.3071
Max Act: 5.9321. Min Act: -0.1700
Data Index: 1670811 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3071. Min Range: -6.3071
Max Act: 5.9008. Min Act: -0.1700
Data Index: 7776998 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3071. Min Range: -6.3071
Max Act: 5.9321. Min Act: -0.1700
Data Index: 5855931 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3071. Min Range: -6.3071
Max Act: 5.8696. Min Act: -0.1700
Data Index: 7480353 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3071. Min Range: -6.3071
Max Act: 5.9008. Min Act: -0.1700
Data Index: 87848 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3071. Min Range: -6.3071
Max Act: 5.9008. Min Act: -0.1700
Data Index: 2235106 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #19