Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6142 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6032. Min Range: -3.6032
Max Act: 3.6032. Min Act: -0.1700
Data Index: 1762288 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6032. Min Range: -3.6032
Max Act: 3.3211. Min Act: -0.1700
Data Index: 713978 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6032. Min Range: -3.6032
Max Act: 3.2741. Min Act: -0.1700
Data Index: 1773557 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6032. Min Range: -3.6032
Max Act: 3.2426. Min Act: -0.1700
Data Index: 3660402 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6032. Min Range: -3.6032
Max Act: 3.2426. Min Act: -0.1700
Data Index: 8180000 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6032. Min Range: -3.6032
Max Act: 3.1955. Min Act: -0.1700
Data Index: 3401745 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6032. Min Range: -3.6032
Max Act: 3.2112. Min Act: -0.1700
Data Index: 4149547 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6032. Min Range: -3.6032
Max Act: 3.1797. Min Act: -0.1700
Data Index: 6410994 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6032. Min Range: -3.6032
Max Act: 3.1955. Min Act: -0.1700
Data Index: 5275792 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6032. Min Range: -3.6032
Max Act: 3.1797. Min Act: -0.1700
Data Index: 6392676 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6032. Min Range: -3.6032
Max Act: 3.1955. Min Act: -0.1700
Data Index: 1020165 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6032. Min Range: -3.6032
Max Act: 3.1797. Min Act: -0.1700
Data Index: 6419939 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6032. Min Range: -3.6032
Max Act: 3.1955. Min Act: -0.1700
Data Index: 422103 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6032. Min Range: -3.6032
Max Act: 3.1797. Min Act: -0.1700
Data Index: 5010173 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6032. Min Range: -3.6032
Max Act: 3.1797. Min Act: -0.1700
Data Index: 3156512 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6032. Min Range: -3.6032
Max Act: 3.1797. Min Act: -0.1700
Data Index: 6026062 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6032. Min Range: -3.6032
Max Act: 3.1797. Min Act: -0.1700
Data Index: 2944841 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6032. Min Range: -3.6032
Max Act: 3.1797. Min Act: -0.1700
Data Index: 1664226 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6032. Min Range: -3.6032
Max Act: 3.1640. Min Act: -0.1700
Data Index: 1444237 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6032. Min Range: -3.6032
Max Act: 3.1483. Min Act: -0.1700
Data Index: 897188 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #19