Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6343 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5687. Min Range: -6.5687
Max Act: 6.5374. Min Act: -0.1700
Data Index: 4656854 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5687. Min Range: -6.5687
Max Act: 6.5687. Min Act: -0.1700
Data Index: 7200281 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5687. Min Range: -6.5687
Max Act: 6.3499. Min Act: -0.1700
Data Index: 8528330 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5687. Min Range: -6.5687
Max Act: 6.2874. Min Act: -0.1700
Data Index: 3353589 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5687. Min Range: -6.5687
Max Act: 6.2249. Min Act: -0.1700
Data Index: 5057134 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5687. Min Range: -6.5687
Max Act: 6.1937. Min Act: -0.1700
Data Index: 7106256 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5687. Min Range: -6.5687
Max Act: 6.1312. Min Act: -0.1700
Data Index: 2249466 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5687. Min Range: -6.5687
Max Act: 6.0999. Min Act: -0.1700
Data Index: 5292263 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5687. Min Range: -6.5687
Max Act: 6.0687. Min Act: -0.1700
Data Index: 7135815 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5687. Min Range: -6.5687
Max Act: 6.0687. Min Act: -0.1700
Data Index: 2005404 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5687. Min Range: -6.5687
Max Act: 6.0687. Min Act: -0.1700
Data Index: 3175140 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5687. Min Range: -6.5687
Max Act: 6.0687. Min Act: -0.1700
Data Index: 5297930 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5687. Min Range: -6.5687
Max Act: 6.0374. Min Act: -0.1700
Data Index: 2748078 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5687. Min Range: -6.5687
Max Act: 6.0062. Min Act: -0.1700
Data Index: 1902714 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5687. Min Range: -6.5687
Max Act: 5.9749. Min Act: -0.1700
Data Index: 6361188 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5687. Min Range: -6.5687
Max Act: 5.9437. Min Act: -0.1700
Data Index: 7660624 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5687. Min Range: -6.5687
Max Act: 5.9437. Min Act: -0.1700
Data Index: 290802 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5687. Min Range: -6.5687
Max Act: 5.9124. Min Act: -0.1700
Data Index: 1264119 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5687. Min Range: -6.5687
Max Act: 5.9437. Min Act: -0.1700
Data Index: 4670827 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5687. Min Range: -6.5687
Max Act: 5.9437. Min Act: -0.1700
Data Index: 5879387 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #19