Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4334 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1887. Min Range: -3.1887
Max Act: 3.1887. Min Act: -0.1700
Data Index: 1220821 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1887. Min Range: -3.1887
Max Act: 3.1887. Min Act: -0.1700
Data Index: 5930770 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1887. Min Range: -3.1887
Max Act: 3.1730. Min Act: -0.1700
Data Index: 6112175 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1887. Min Range: -3.1887
Max Act: 3.1415. Min Act: -0.1700
Data Index: 3747100 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1887. Min Range: -3.1887
Max Act: 3.1572. Min Act: -0.1700
Data Index: 6575691 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1887. Min Range: -3.1887
Max Act: 3.1572. Min Act: -0.1700
Data Index: 6401969 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1887. Min Range: -3.1887
Max Act: 3.1415. Min Act: -0.1700
Data Index: 7012538 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1887. Min Range: -3.1887
Max Act: 3.1415. Min Act: -0.1700
Data Index: 1169723 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1887. Min Range: -3.1887
Max Act: 3.1415. Min Act: -0.1700
Data Index: 6009685 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1887. Min Range: -3.1887
Max Act: 3.1100. Min Act: -0.1700
Data Index: 7400465 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1887. Min Range: -3.1887
Max Act: 3.1257. Min Act: -0.1700
Data Index: 179556 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1887. Min Range: -3.1887
Max Act: 3.1257. Min Act: -0.1700
Data Index: 3543949 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1887. Min Range: -3.1887
Max Act: 3.1257. Min Act: -0.1700
Data Index: 1034816 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1887. Min Range: -3.1887
Max Act: 3.1257. Min Act: -0.1700
Data Index: 5825598 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1887. Min Range: -3.1887
Max Act: 3.1100. Min Act: -0.1700
Data Index: 6094789 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1887. Min Range: -3.1887
Max Act: 3.1100. Min Act: -0.1700
Data Index: 6319108 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1887. Min Range: -3.1887
Max Act: 3.1100. Min Act: -0.1700
Data Index: 2141079 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1887. Min Range: -3.1887
Max Act: 3.0942. Min Act: -0.1700
Data Index: 1638342 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1887. Min Range: -3.1887
Max Act: 3.1100. Min Act: -0.1700
Data Index: 5420392 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1887. Min Range: -3.1887
Max Act: 3.1100. Min Act: -0.1700
Data Index: 5170119 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #19