Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5505 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7001. Min Range: -3.7001
Max Act: 3.7001. Min Act: -0.1700
Data Index: 7060930 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7001. Min Range: -3.7001
Max Act: 3.6688. Min Act: -0.1700
Data Index: 3135397 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7001. Min Range: -3.7001
Max Act: 3.6688. Min Act: -0.1700
Data Index: 6242225 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7001. Min Range: -3.7001
Max Act: 3.6688. Min Act: -0.1700
Data Index: 3657882 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7001. Min Range: -3.7001
Max Act: 3.6375. Min Act: -0.1700
Data Index: 5430957 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7001. Min Range: -3.7001
Max Act: 3.6375. Min Act: -0.1700
Data Index: 5524091 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7001. Min Range: -3.7001
Max Act: 3.6062. Min Act: -0.1700
Data Index: 1104018 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7001. Min Range: -3.7001
Max Act: 3.6062. Min Act: -0.1700
Data Index: 979869 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7001. Min Range: -3.7001
Max Act: 3.6062. Min Act: -0.1700
Data Index: 4617083 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7001. Min Range: -3.7001
Max Act: 3.6062. Min Act: -0.1700
Data Index: 8332785 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7001. Min Range: -3.7001
Max Act: 3.6062. Min Act: -0.1700
Data Index: 3548247 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7001. Min Range: -3.7001
Max Act: 3.5749. Min Act: -0.1700
Data Index: 5430959 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7001. Min Range: -3.7001
Max Act: 3.5749. Min Act: -0.1700
Data Index: 2468028 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7001. Min Range: -3.7001
Max Act: 3.5749. Min Act: -0.1700
Data Index: 4209359 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7001. Min Range: -3.7001
Max Act: 3.5436. Min Act: -0.1700
Data Index: 2550059 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7001. Min Range: -3.7001
Max Act: 3.5749. Min Act: -0.1700
Data Index: 5811860 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7001. Min Range: -3.7001
Max Act: 3.5749. Min Act: -0.1700
Data Index: 2731595 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7001. Min Range: -3.7001
Max Act: 3.5749. Min Act: -0.1700
Data Index: 6002900 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7001. Min Range: -3.7001
Max Act: 3.5749. Min Act: -0.1700
Data Index: 4985009 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7001. Min Range: -3.7001
Max Act: 3.5749. Min Act: -0.1700
Data Index: 453673 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #19