Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3531 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7747. Min Range: -6.7747
Max Act: 6.7747. Min Act: -0.1700
Data Index: 5539227 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7747. Min Range: -6.7747
Max Act: 6.3685. Min Act: -0.1700
Data Index: 3175421 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7747. Min Range: -6.7747
Max Act: 6.3372. Min Act: -0.1700
Data Index: 7662459 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7747. Min Range: -6.7747
Max Act: 6.3060. Min Act: -0.1700
Data Index: 7033087 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7747. Min Range: -6.7747
Max Act: 6.2122. Min Act: -0.1700
Data Index: 6608769 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7747. Min Range: -6.7747
Max Act: 6.2122. Min Act: -0.1700
Data Index: 2336962 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7747. Min Range: -6.7747
Max Act: 6.1810. Min Act: -0.1700
Data Index: 1047376 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7747. Min Range: -6.7747
Max Act: 6.1497. Min Act: -0.1700
Data Index: 5826402 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7747. Min Range: -6.7747
Max Act: 6.0560. Min Act: -0.1700
Data Index: 4626478 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7747. Min Range: -6.7747
Max Act: 5.9935. Min Act: -0.1700
Data Index: 7641609 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7747. Min Range: -6.7747
Max Act: 6.0560. Min Act: -0.1700
Data Index: 3960327 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7747. Min Range: -6.7747
Max Act: 6.0560. Min Act: -0.1700
Data Index: 1479292 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7747. Min Range: -6.7747
Max Act: 6.0247. Min Act: -0.1700
Data Index: 1379004 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7747. Min Range: -6.7747
Max Act: 5.9935. Min Act: -0.1700
Data Index: 2775164 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7747. Min Range: -6.7747
Max Act: 5.9935. Min Act: -0.1700
Data Index: 2438597 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7747. Min Range: -6.7747
Max Act: 5.9935. Min Act: -0.1700
Data Index: 38440 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7747. Min Range: -6.7747
Max Act: 5.9310. Min Act: -0.1700
Data Index: 3850180 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7747. Min Range: -6.7747
Max Act: 5.9310. Min Act: -0.1700
Data Index: 694036 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7747. Min Range: -6.7747
Max Act: 5.9622. Min Act: -0.1700
Data Index: 1640989 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7747. Min Range: -6.7747
Max Act: 5.9310. Min Act: -0.1700
Data Index: 950125 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #19