Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2633 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5200. Min Range: -6.5200
Max Act: 6.5200. Min Act: -0.1700
Data Index: 1131873 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5200. Min Range: -6.5200
Max Act: 6.3325. Min Act: -0.1700
Data Index: 1312380 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5200. Min Range: -6.5200
Max Act: 6.3325. Min Act: -0.1700
Data Index: 5667898 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5200. Min Range: -6.5200
Max Act: 6.2700. Min Act: -0.1700
Data Index: 7279925 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5200. Min Range: -6.5200
Max Act: 6.2075. Min Act: -0.1700
Data Index: 5081102 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5200. Min Range: -6.5200
Max Act: 6.2387. Min Act: -0.1700
Data Index: 2053910 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5200. Min Range: -6.5200
Max Act: 6.2075. Min Act: -0.1700
Data Index: 801183 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5200. Min Range: -6.5200
Max Act: 6.1450. Min Act: -0.1700
Data Index: 440113 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5200. Min Range: -6.5200
Max Act: 6.1137. Min Act: -0.1700
Data Index: 1157303 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5200. Min Range: -6.5200
Max Act: 6.0825. Min Act: -0.1700
Data Index: 5653749 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5200. Min Range: -6.5200
Max Act: 6.0825. Min Act: -0.1700
Data Index: 6124854 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5200. Min Range: -6.5200
Max Act: 5.9887. Min Act: -0.1700
Data Index: 5831861 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5200. Min Range: -6.5200
Max Act: 5.9887. Min Act: -0.1700
Data Index: 7525000 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5200. Min Range: -6.5200
Max Act: 5.9575. Min Act: -0.1700
Data Index: 5196909 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5200. Min Range: -6.5200
Max Act: 5.9262. Min Act: -0.1700
Data Index: 4827892 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5200. Min Range: -6.5200
Max Act: 5.9262. Min Act: -0.1700
Data Index: 8077774 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5200. Min Range: -6.5200
Max Act: 5.8950. Min Act: -0.1700
Data Index: 2994021 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5200. Min Range: -6.5200
Max Act: 5.8637. Min Act: -0.1700
Data Index: 3846876 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5200. Min Range: -6.5200
Max Act: 5.8637. Min Act: -0.1700
Data Index: 2448184 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5200. Min Range: -6.5200
Max Act: 5.8637. Min Act: -0.1700
Data Index: 7344180 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #19