Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5322 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0190. Min Range: -6.0190
Max Act: 6.0190. Min Act: -0.1700
Data Index: 1841353 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0190. Min Range: -6.0190
Max Act: 5.8940. Min Act: -0.1700
Data Index: 4293387 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0190. Min Range: -6.0190
Max Act: 5.8628. Min Act: -0.1700
Data Index: 7932013 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0190. Min Range: -6.0190
Max Act: 5.8315. Min Act: -0.1700
Data Index: 5977571 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0190. Min Range: -6.0190
Max Act: 5.8315. Min Act: -0.1700
Data Index: 106476 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0190. Min Range: -6.0190
Max Act: 5.8315. Min Act: -0.1700
Data Index: 7919635 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0190. Min Range: -6.0190
Max Act: 5.8003. Min Act: -0.1700
Data Index: 661116 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0190. Min Range: -6.0190
Max Act: 5.8003. Min Act: -0.1700
Data Index: 3350334 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0190. Min Range: -6.0190
Max Act: 5.7690. Min Act: -0.1700
Data Index: 6765981 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0190. Min Range: -6.0190
Max Act: 5.7690. Min Act: -0.1700
Data Index: 1866552 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0190. Min Range: -6.0190
Max Act: 5.7065. Min Act: -0.1700
Data Index: 1591067 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0190. Min Range: -6.0190
Max Act: 5.6753. Min Act: -0.1700
Data Index: 3094825 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0190. Min Range: -6.0190
Max Act: 5.6753. Min Act: -0.1700
Data Index: 5917537 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0190. Min Range: -6.0190
Max Act: 5.6128. Min Act: -0.1700
Data Index: 1180612 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0190. Min Range: -6.0190
Max Act: 5.5815. Min Act: -0.1700
Data Index: 4842095 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0190. Min Range: -6.0190
Max Act: 5.5815. Min Act: -0.1700
Data Index: 8271053 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0190. Min Range: -6.0190
Max Act: 5.5815. Min Act: -0.1700
Data Index: 3022205 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0190. Min Range: -6.0190
Max Act: 5.5815. Min Act: -0.1700
Data Index: 8628769 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0190. Min Range: -6.0190
Max Act: 5.5503. Min Act: -0.1700
Data Index: 1805499 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0190. Min Range: -6.0190
Max Act: 5.5503. Min Act: -0.1700
Data Index: 3032830 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19