Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2850 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7839. Min Range: -8.7839
Max Act: 8.7839. Min Act: -0.1700
Data Index: 4638035 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7839. Min Range: -8.7839
Max Act: 8.6589. Min Act: -0.1700
Data Index: 6776614 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7839. Min Range: -8.7839
Max Act: 8.4714. Min Act: -0.1700
Data Index: 7713326 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7839. Min Range: -8.7839
Max Act: 8.3464. Min Act: -0.1700
Data Index: 4700762 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7839. Min Range: -8.7839
Max Act: 7.9402. Min Act: -0.1700
Data Index: 568866 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7839. Min Range: -8.7839
Max Act: 7.8777. Min Act: -0.1700
Data Index: 6323066 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7839. Min Range: -8.7839
Max Act: 7.8777. Min Act: -0.1700
Data Index: 6762090 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7839. Min Range: -8.7839
Max Act: 7.8777. Min Act: -0.1700
Data Index: 3669408 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7839. Min Range: -8.7839
Max Act: 7.8777. Min Act: -0.1700
Data Index: 2527287 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7839. Min Range: -8.7839
Max Act: 7.7839. Min Act: -0.1700
Data Index: 7245236 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7839. Min Range: -8.7839
Max Act: 7.7839. Min Act: -0.1700
Data Index: 451842 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7839. Min Range: -8.7839
Max Act: 7.7527. Min Act: -0.1700
Data Index: 2804620 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7839. Min Range: -8.7839
Max Act: 7.7527. Min Act: -0.1700
Data Index: 715435 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7839. Min Range: -8.7839
Max Act: 7.7214. Min Act: -0.1700
Data Index: 2616457 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7839. Min Range: -8.7839
Max Act: 7.7214. Min Act: -0.1700
Data Index: 4059321 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7839. Min Range: -8.7839
Max Act: 7.6589. Min Act: -0.1700
Data Index: 4749462 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7839. Min Range: -8.7839
Max Act: 7.7214. Min Act: -0.1700
Data Index: 7518307 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7839. Min Range: -8.7839
Max Act: 7.6589. Min Act: -0.1700
Data Index: 5450489 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7839. Min Range: -8.7839
Max Act: 7.6589. Min Act: -0.1700
Data Index: 45762 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7839. Min Range: -8.7839
Max Act: 7.6589. Min Act: -0.1700
Data Index: 5253484 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #19