Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3517 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2533. Min Range: -8.2533
Max Act: 8.2533. Min Act: -0.1700
Data Index: 237491 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2533. Min Range: -8.2533
Max Act: 8.1283. Min Act: -0.1700
Data Index: 6438784 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2533. Min Range: -8.2533
Max Act: 8.0345. Min Act: -0.1700
Data Index: 2064114 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2533. Min Range: -8.2533
Max Act: 7.9408. Min Act: -0.1700
Data Index: 3989505 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2533. Min Range: -8.2533
Max Act: 7.9408. Min Act: -0.1700
Data Index: 698495 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2533. Min Range: -8.2533
Max Act: 7.8783. Min Act: -0.1700
Data Index: 30998 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2533. Min Range: -8.2533
Max Act: 7.8783. Min Act: -0.1700
Data Index: 6256829 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2533. Min Range: -8.2533
Max Act: 7.8470. Min Act: -0.1700
Data Index: 4413799 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2533. Min Range: -8.2533
Max Act: 7.8470. Min Act: -0.1700
Data Index: 3200724 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2533. Min Range: -8.2533
Max Act: 7.8158. Min Act: -0.1700
Data Index: 6889122 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2533. Min Range: -8.2533
Max Act: 7.7533. Min Act: -0.1700
Data Index: 539692 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2533. Min Range: -8.2533
Max Act: 7.7845. Min Act: -0.1700
Data Index: 1370672 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2533. Min Range: -8.2533
Max Act: 7.7845. Min Act: -0.1700
Data Index: 216095 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2533. Min Range: -8.2533
Max Act: 7.7845. Min Act: -0.1700
Data Index: 5456172 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2533. Min Range: -8.2533
Max Act: 7.7220. Min Act: -0.1700
Data Index: 5246027 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2533. Min Range: -8.2533
Max Act: 7.7220. Min Act: -0.1700
Data Index: 4076445 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2533. Min Range: -8.2533
Max Act: 7.6908. Min Act: -0.1700
Data Index: 97491 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2533. Min Range: -8.2533
Max Act: 7.6908. Min Act: -0.1700
Data Index: 4593805 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2533. Min Range: -8.2533
Max Act: 7.7220. Min Act: -0.1700
Data Index: 8818724 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2533. Min Range: -8.2533
Max Act: 7.6595. Min Act: -0.1700
Data Index: 6327288 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #19