Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6131 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0594. Min Range: -5.0594
Max Act: 5.0594. Min Act: -0.1700
Data Index: 8204629 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0594. Min Range: -5.0594
Max Act: 4.9031. Min Act: -0.1700
Data Index: 8094644 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0594. Min Range: -5.0594
Max Act: 4.8719. Min Act: -0.1700
Data Index: 1186379 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0594. Min Range: -5.0594
Max Act: 4.8406. Min Act: -0.1700
Data Index: 5662791 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0594. Min Range: -5.0594
Max Act: 4.8094. Min Act: -0.1700
Data Index: 5662790 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0594. Min Range: -5.0594
Max Act: 4.7156. Min Act: -0.1700
Data Index: 1659337 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0594. Min Range: -5.0594
Max Act: 4.7469. Min Act: -0.1700
Data Index: 3623868 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0594. Min Range: -5.0594
Max Act: 4.7781. Min Act: -0.1700
Data Index: 5994576 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0594. Min Range: -5.0594
Max Act: 4.7156. Min Act: -0.1700
Data Index: 8121632 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0594. Min Range: -5.0594
Max Act: 4.7156. Min Act: -0.1700
Data Index: 8235548 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0594. Min Range: -5.0594
Max Act: 4.6844. Min Act: -0.1700
Data Index: 3100038 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0594. Min Range: -5.0594
Max Act: 4.6844. Min Act: -0.1700
Data Index: 4019284 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0594. Min Range: -5.0594
Max Act: 4.6844. Min Act: -0.1700
Data Index: 8610321 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0594. Min Range: -5.0594
Max Act: 4.6844. Min Act: -0.1700
Data Index: 5009148 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0594. Min Range: -5.0594
Max Act: 4.6531. Min Act: -0.1700
Data Index: 5744583 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0594. Min Range: -5.0594
Max Act: 4.6531. Min Act: -0.1700
Data Index: 4595020 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0594. Min Range: -5.0594
Max Act: 4.6531. Min Act: -0.1700
Data Index: 5339108 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0594. Min Range: -5.0594
Max Act: 4.6531. Min Act: -0.1700
Data Index: 3531093 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0594. Min Range: -5.0594
Max Act: 4.6531. Min Act: -0.1700
Data Index: 7902374 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0594. Min Range: -5.0594
Max Act: 4.6531. Min Act: -0.1700
Data Index: 4610362 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #19