Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2575 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5462. Min Range: -5.5462
Max Act: 5.5462. Min Act: -0.1700
Data Index: 5851399 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5462. Min Range: -5.5462
Max Act: 5.5462. Min Act: -0.1700
Data Index: 232376 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5462. Min Range: -5.5462
Max Act: 5.5150. Min Act: -0.1700
Data Index: 7808711 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5462. Min Range: -5.5462
Max Act: 5.3900. Min Act: -0.1700
Data Index: 4105099 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5462. Min Range: -5.5462
Max Act: 5.3275. Min Act: -0.1700
Data Index: 7788950 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5462. Min Range: -5.5462
Max Act: 5.2962. Min Act: -0.1700
Data Index: 2631939 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5462. Min Range: -5.5462
Max Act: 5.2962. Min Act: -0.1700
Data Index: 2821990 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5462. Min Range: -5.5462
Max Act: 5.2962. Min Act: -0.1700
Data Index: 3206196 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5462. Min Range: -5.5462
Max Act: 5.2650. Min Act: -0.1700
Data Index: 1597988 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5462. Min Range: -5.5462
Max Act: 5.2337. Min Act: -0.1700
Data Index: 478475 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5462. Min Range: -5.5462
Max Act: 5.2337. Min Act: -0.1700
Data Index: 1182193 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5462. Min Range: -5.5462
Max Act: 5.2337. Min Act: -0.1700
Data Index: 8156364 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5462. Min Range: -5.5462
Max Act: 5.2025. Min Act: -0.1700
Data Index: 5820130 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5462. Min Range: -5.5462
Max Act: 5.1712. Min Act: -0.1700
Data Index: 3917159 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5462. Min Range: -5.5462
Max Act: 5.2025. Min Act: -0.1700
Data Index: 3906275 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5462. Min Range: -5.5462
Max Act: 5.1712. Min Act: -0.1700
Data Index: 8525489 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5462. Min Range: -5.5462
Max Act: 5.2025. Min Act: -0.1700
Data Index: 853241 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5462. Min Range: -5.5462
Max Act: 5.1712. Min Act: -0.1700
Data Index: 3982712 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5462. Min Range: -5.5462
Max Act: 5.1712. Min Act: -0.1700
Data Index: 8120696 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5462. Min Range: -5.5462
Max Act: 5.1712. Min Act: -0.1700
Data Index: 7662882 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #19