Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5296 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5687. Min Range: -8.5687
Max Act: 8.5687. Min Act: -0.1700
Data Index: 7204014 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5687. Min Range: -8.5687
Max Act: 8.3187. Min Act: -0.1700
Data Index: 5513352 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5687. Min Range: -8.5687
Max Act: 8.2562. Min Act: -0.1700
Data Index: 4642031 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5687. Min Range: -8.5687
Max Act: 8.1937. Min Act: -0.1700
Data Index: 8323629 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5687. Min Range: -8.5687
Max Act: 8.1937. Min Act: -0.1700
Data Index: 923924 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5687. Min Range: -8.5687
Max Act: 8.1312. Min Act: -0.1700
Data Index: 1608508 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5687. Min Range: -8.5687
Max Act: 8.0687. Min Act: -0.1700
Data Index: 5417483 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5687. Min Range: -8.5687
Max Act: 8.0687. Min Act: -0.1700
Data Index: 4419728 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5687. Min Range: -8.5687
Max Act: 8.0062. Min Act: -0.1700
Data Index: 8213477 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5687. Min Range: -8.5687
Max Act: 8.0062. Min Act: -0.1700
Data Index: 6819803 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5687. Min Range: -8.5687
Max Act: 8.0062. Min Act: -0.1700
Data Index: 6717203 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5687. Min Range: -8.5687
Max Act: 8.0062. Min Act: -0.1700
Data Index: 5265321 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5687. Min Range: -8.5687
Max Act: 8.0062. Min Act: -0.1700
Data Index: 1801525 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5687. Min Range: -8.5687
Max Act: 7.9437. Min Act: -0.1700
Data Index: 83289 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5687. Min Range: -8.5687
Max Act: 7.8812. Min Act: -0.1700
Data Index: 6592394 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5687. Min Range: -8.5687
Max Act: 7.8812. Min Act: -0.1700
Data Index: 3246113 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5687. Min Range: -8.5687
Max Act: 7.8812. Min Act: -0.1700
Data Index: 866528 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5687. Min Range: -8.5687
Max Act: 7.8812. Min Act: -0.1700
Data Index: 324715 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5687. Min Range: -8.5687
Max Act: 7.8812. Min Act: -0.1700
Data Index: 5458388 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5687. Min Range: -8.5687
Max Act: 7.8812. Min Act: -0.1700
Data Index: 2476271 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #19