Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 60 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7133. Min Range: -7.7133
Max Act: 7.7133. Min Act: -0.1700
Data Index: 3614055 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7133. Min Range: -7.7133
Max Act: 7.2446. Min Act: -0.1700
Data Index: 2223626 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7133. Min Range: -7.7133
Max Act: 6.9633. Min Act: -0.1700
Data Index: 4262806 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7133. Min Range: -7.7133
Max Act: 6.8383. Min Act: -0.1700
Data Index: 8394065 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7133. Min Range: -7.7133
Max Act: 6.7758. Min Act: -0.1700
Data Index: 7259946 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7133. Min Range: -7.7133
Max Act: 6.7446. Min Act: -0.1700
Data Index: 3600723 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7133. Min Range: -7.7133
Max Act: 6.7133. Min Act: -0.1700
Data Index: 7327114 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7133. Min Range: -7.7133
Max Act: 6.7133. Min Act: -0.1700
Data Index: 634945 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7133. Min Range: -7.7133
Max Act: 6.6821. Min Act: -0.1700
Data Index: 8419453 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7133. Min Range: -7.7133
Max Act: 6.6821. Min Act: -0.1700
Data Index: 3484048 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7133. Min Range: -7.7133
Max Act: 6.6196. Min Act: -0.1700
Data Index: 2375666 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7133. Min Range: -7.7133
Max Act: 6.5883. Min Act: -0.1700
Data Index: 6203683 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7133. Min Range: -7.7133
Max Act: 6.6196. Min Act: -0.1700
Data Index: 6716351 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7133. Min Range: -7.7133
Max Act: 6.5883. Min Act: -0.1700
Data Index: 7802523 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7133. Min Range: -7.7133
Max Act: 6.5571. Min Act: -0.1700
Data Index: 6096302 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7133. Min Range: -7.7133
Max Act: 6.5571. Min Act: -0.1700
Data Index: 7414861 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7133. Min Range: -7.7133
Max Act: 6.5258. Min Act: -0.1700
Data Index: 594688 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7133. Min Range: -7.7133
Max Act: 6.5258. Min Act: -0.1700
Data Index: 177574 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7133. Min Range: -7.7133
Max Act: 6.4946. Min Act: -0.1700
Data Index: 4840895 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7133. Min Range: -7.7133
Max Act: 6.4946. Min Act: -0.1700
Data Index: 4536193 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #19