Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3052 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0919. Min Range: -7.0919
Max Act: 7.0919. Min Act: -0.1700
Data Index: 7168425 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0919. Min Range: -7.0919
Max Act: 7.0607. Min Act: -0.1700
Data Index: 8628678 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0919. Min Range: -7.0919
Max Act: 6.9982. Min Act: -0.1700
Data Index: 5944719 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0919. Min Range: -7.0919
Max Act: 6.9357. Min Act: -0.1700
Data Index: 3397773 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0919. Min Range: -7.0919
Max Act: 6.9669. Min Act: -0.1700
Data Index: 6258130 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0919. Min Range: -7.0919
Max Act: 6.9357. Min Act: -0.1700
Data Index: 1952396 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0919. Min Range: -7.0919
Max Act: 6.9044. Min Act: -0.1700
Data Index: 467439 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0919. Min Range: -7.0919
Max Act: 6.9044. Min Act: -0.1700
Data Index: 7217718 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0919. Min Range: -7.0919
Max Act: 6.9044. Min Act: -0.1700
Data Index: 3198338 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0919. Min Range: -7.0919
Max Act: 6.8732. Min Act: -0.1700
Data Index: 6834000 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0919. Min Range: -7.0919
Max Act: 6.8732. Min Act: -0.1700
Data Index: 5476057 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0919. Min Range: -7.0919
Max Act: 6.8732. Min Act: -0.1700
Data Index: 7215677 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0919. Min Range: -7.0919
Max Act: 6.8107. Min Act: -0.1700
Data Index: 1331773 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0919. Min Range: -7.0919
Max Act: 6.8732. Min Act: -0.1700
Data Index: 6248348 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0919. Min Range: -7.0919
Max Act: 6.8107. Min Act: -0.1700
Data Index: 7311859 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0919. Min Range: -7.0919
Max Act: 6.7482. Min Act: -0.1700
Data Index: 1879255 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0919. Min Range: -7.0919
Max Act: 6.7794. Min Act: -0.1700
Data Index: 5674826 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0919. Min Range: -7.0919
Max Act: 6.7794. Min Act: -0.1700
Data Index: 3449226 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0919. Min Range: -7.0919
Max Act: 6.6857. Min Act: -0.1700
Data Index: 7500400 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0919. Min Range: -7.0919
Max Act: 6.6857. Min Act: -0.1700
Data Index: 8177213 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #19