Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3484 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2509. Min Range: -6.2509
Max Act: 6.2509. Min Act: -0.1700
Data Index: 6237534 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2509. Min Range: -6.2509
Max Act: 6.1884. Min Act: -0.1700
Data Index: 301342 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2509. Min Range: -6.2509
Max Act: 6.1259. Min Act: -0.1700
Data Index: 6252915 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2509. Min Range: -6.2509
Max Act: 6.1259. Min Act: -0.1700
Data Index: 8214597 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2509. Min Range: -6.2509
Max Act: 6.1259. Min Act: -0.1700
Data Index: 7145742 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2509. Min Range: -6.2509
Max Act: 6.0634. Min Act: -0.1700
Data Index: 4533985 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2509. Min Range: -6.2509
Max Act: 6.0634. Min Act: -0.1700
Data Index: 5106 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2509. Min Range: -6.2509
Max Act: 6.0322. Min Act: -0.1700
Data Index: 2229513 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2509. Min Range: -6.2509
Max Act: 6.0009. Min Act: -0.1700
Data Index: 7680540 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2509. Min Range: -6.2509
Max Act: 5.9697. Min Act: -0.1700
Data Index: 3365785 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2509. Min Range: -6.2509
Max Act: 5.9697. Min Act: -0.1700
Data Index: 5092607 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2509. Min Range: -6.2509
Max Act: 5.9697. Min Act: -0.1700
Data Index: 7790023 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2509. Min Range: -6.2509
Max Act: 5.9697. Min Act: -0.1700
Data Index: 3031818 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2509. Min Range: -6.2509
Max Act: 5.9697. Min Act: -0.1700
Data Index: 3102783 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2509. Min Range: -6.2509
Max Act: 5.9697. Min Act: -0.1700
Data Index: 5037892 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2509. Min Range: -6.2509
Max Act: 5.9384. Min Act: -0.1700
Data Index: 391961 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2509. Min Range: -6.2509
Max Act: 5.9384. Min Act: -0.1700
Data Index: 8525224 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2509. Min Range: -6.2509
Max Act: 5.9384. Min Act: -0.1700
Data Index: 2769325 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2509. Min Range: -6.2509
Max Act: 5.9072. Min Act: -0.1700
Data Index: 7680532 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2509. Min Range: -6.2509
Max Act: 5.9072. Min Act: -0.1700
Data Index: 901062 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #19