Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1938 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6139. Min Range: -6.6139
Max Act: 6.6139. Min Act: -0.1700
Data Index: 4598724 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6139. Min Range: -6.6139
Max Act: 6.4264. Min Act: -0.1700
Data Index: 8782479 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6139. Min Range: -6.6139
Max Act: 6.3639. Min Act: -0.1700
Data Index: 449980 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6139. Min Range: -6.6139
Max Act: 6.3327. Min Act: -0.1700
Data Index: 5096174 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6139. Min Range: -6.6139
Max Act: 6.3014. Min Act: -0.1700
Data Index: 3069388 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6139. Min Range: -6.6139
Max Act: 6.2077. Min Act: -0.1700
Data Index: 1534293 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6139. Min Range: -6.6139
Max Act: 6.1452. Min Act: -0.1700
Data Index: 536216 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6139. Min Range: -6.6139
Max Act: 6.1452. Min Act: -0.1700
Data Index: 5413807 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6139. Min Range: -6.6139
Max Act: 6.1139. Min Act: -0.1700
Data Index: 3102868 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6139. Min Range: -6.6139
Max Act: 6.0514. Min Act: -0.1700
Data Index: 8561111 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6139. Min Range: -6.6139
Max Act: 6.0514. Min Act: -0.1700
Data Index: 901747 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6139. Min Range: -6.6139
Max Act: 6.0202. Min Act: -0.1700
Data Index: 4841303 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6139. Min Range: -6.6139
Max Act: 6.0514. Min Act: -0.1700
Data Index: 843585 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6139. Min Range: -6.6139
Max Act: 6.0202. Min Act: -0.1700
Data Index: 4803508 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6139. Min Range: -6.6139
Max Act: 5.9577. Min Act: -0.1700
Data Index: 213083 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6139. Min Range: -6.6139
Max Act: 5.9577. Min Act: -0.1700
Data Index: 5547336 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6139. Min Range: -6.6139
Max Act: 5.9577. Min Act: -0.1700
Data Index: 6683653 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6139. Min Range: -6.6139
Max Act: 5.9577. Min Act: -0.1700
Data Index: 1517466 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6139. Min Range: -6.6139
Max Act: 5.9264. Min Act: -0.1700
Data Index: 3303807 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6139. Min Range: -6.6139
Max Act: 5.9264. Min Act: -0.1700
Data Index: 7242782 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #19