Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2414 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.3280. Min Range: -10.3280
Max Act: 10.3280. Min Act: -0.1700
Data Index: 2046823 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3280. Min Range: -10.3280
Max Act: 9.3905. Min Act: -0.1700
Data Index: 164805 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3280. Min Range: -10.3280
Max Act: 9.1405. Min Act: -0.1700
Data Index: 5383866 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3280. Min Range: -10.3280
Max Act: 9.0780. Min Act: -0.1700
Data Index: 2626909 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3280. Min Range: -10.3280
Max Act: 8.9530. Min Act: -0.1700
Data Index: 3516694 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3280. Min Range: -10.3280
Max Act: 8.8905. Min Act: -0.1700
Data Index: 43870 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3280. Min Range: -10.3280
Max Act: 8.8280. Min Act: -0.1700
Data Index: 6362007 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3280. Min Range: -10.3280
Max Act: 8.8280. Min Act: -0.1700
Data Index: 8253839 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3280. Min Range: -10.3280
Max Act: 8.7030. Min Act: -0.1700
Data Index: 3155763 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3280. Min Range: -10.3280
Max Act: 8.7030. Min Act: -0.1700
Data Index: 7428468 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3280. Min Range: -10.3280
Max Act: 8.7030. Min Act: -0.1700
Data Index: 7110449 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3280. Min Range: -10.3280
Max Act: 8.7030. Min Act: -0.1700
Data Index: 8235423 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3280. Min Range: -10.3280
Max Act: 8.7030. Min Act: -0.1700
Data Index: 8057403 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3280. Min Range: -10.3280
Max Act: 8.7030. Min Act: -0.1700
Data Index: 6661900 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3280. Min Range: -10.3280
Max Act: 8.6405. Min Act: -0.1700
Data Index: 5525990 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3280. Min Range: -10.3280
Max Act: 8.5780. Min Act: -0.1700
Data Index: 2176061 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3280. Min Range: -10.3280
Max Act: 8.5780. Min Act: -0.1700
Data Index: 5564010 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3280. Min Range: -10.3280
Max Act: 8.5780. Min Act: -0.1700
Data Index: 6439115 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3280. Min Range: -10.3280
Max Act: 8.5780. Min Act: -0.1700
Data Index: 7972873 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3280. Min Range: -10.3280
Max Act: 8.5780. Min Act: -0.1700
Data Index: 4435052 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #19