Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3352 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1844. Min Range: -6.1844
Max Act: 6.1844. Min Act: -0.1700
Data Index: 7560179 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1844. Min Range: -6.1844
Max Act: 5.9031. Min Act: -0.1700
Data Index: 8396790 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1844. Min Range: -6.1844
Max Act: 5.8719. Min Act: -0.1700
Data Index: 3778653 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1844. Min Range: -6.1844
Max Act: 5.7781. Min Act: -0.1700
Data Index: 6451811 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1844. Min Range: -6.1844
Max Act: 5.7781. Min Act: -0.1700
Data Index: 4586580 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1844. Min Range: -6.1844
Max Act: 5.7781. Min Act: -0.1700
Data Index: 1138018 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1844. Min Range: -6.1844
Max Act: 5.7469. Min Act: -0.1700
Data Index: 8777557 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1844. Min Range: -6.1844
Max Act: 5.7469. Min Act: -0.1700
Data Index: 1968811 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1844. Min Range: -6.1844
Max Act: 5.7781. Min Act: -0.1700
Data Index: 8465761 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1844. Min Range: -6.1844
Max Act: 5.7156. Min Act: -0.1700
Data Index: 5392446 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1844. Min Range: -6.1844
Max Act: 5.6844. Min Act: -0.1700
Data Index: 8160248 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1844. Min Range: -6.1844
Max Act: 5.6844. Min Act: -0.1700
Data Index: 2752917 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1844. Min Range: -6.1844
Max Act: 5.6219. Min Act: -0.1700
Data Index: 2901087 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1844. Min Range: -6.1844
Max Act: 5.6531. Min Act: -0.1700
Data Index: 3161675 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1844. Min Range: -6.1844
Max Act: 5.6531. Min Act: -0.1700
Data Index: 5351145 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1844. Min Range: -6.1844
Max Act: 5.6531. Min Act: -0.1700
Data Index: 8416761 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1844. Min Range: -6.1844
Max Act: 5.6531. Min Act: -0.1700
Data Index: 5732853 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1844. Min Range: -6.1844
Max Act: 5.6219. Min Act: -0.1700
Data Index: 6211830 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1844. Min Range: -6.1844
Max Act: 5.6219. Min Act: -0.1700
Data Index: 7728850 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1844. Min Range: -6.1844
Max Act: 5.6219. Min Act: -0.1700
Data Index: 2829002 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #19