Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3552 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8275. Min Range: -8.8275
Max Act: 8.8275. Min Act: -0.1700
Data Index: 3700558 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8275. Min Range: -8.8275
Max Act: 8.5775. Min Act: -0.1700
Data Index: 2467697 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8275. Min Range: -8.8275
Max Act: 8.4525. Min Act: -0.1700
Data Index: 4532878 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8275. Min Range: -8.8275
Max Act: 8.5150. Min Act: -0.1700
Data Index: 4457270 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8275. Min Range: -8.8275
Max Act: 8.4525. Min Act: -0.1700
Data Index: 7595173 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8275. Min Range: -8.8275
Max Act: 8.3900. Min Act: -0.1700
Data Index: 2622923 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8275. Min Range: -8.8275
Max Act: 8.3900. Min Act: -0.1700
Data Index: 2036463 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8275. Min Range: -8.8275
Max Act: 8.3900. Min Act: -0.1700
Data Index: 7874583 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8275. Min Range: -8.8275
Max Act: 8.3900. Min Act: -0.1700
Data Index: 7606740 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8275. Min Range: -8.8275
Max Act: 8.3275. Min Act: -0.1700
Data Index: 1498830 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8275. Min Range: -8.8275
Max Act: 8.3275. Min Act: -0.1700
Data Index: 3682804 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8275. Min Range: -8.8275
Max Act: 8.3275. Min Act: -0.1700
Data Index: 3806174 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8275. Min Range: -8.8275
Max Act: 8.2650. Min Act: -0.1700
Data Index: 5043834 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8275. Min Range: -8.8275
Max Act: 8.2650. Min Act: -0.1700
Data Index: 2899204 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8275. Min Range: -8.8275
Max Act: 8.2025. Min Act: -0.1700
Data Index: 2445709 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8275. Min Range: -8.8275
Max Act: 8.2025. Min Act: -0.1700
Data Index: 8701537 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8275. Min Range: -8.8275
Max Act: 8.2025. Min Act: -0.1700
Data Index: 1967428 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8275. Min Range: -8.8275
Max Act: 8.2025. Min Act: -0.1700
Data Index: 3894480 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8275. Min Range: -8.8275
Max Act: 8.2025. Min Act: -0.1700
Data Index: 5092955 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8275. Min Range: -8.8275
Max Act: 8.1400. Min Act: -0.1700
Data Index: 5261955 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #19