Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3530 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0154. Min Range: -5.0154
Max Act: 5.0154. Min Act: -0.1700
Data Index: 8408416 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0154. Min Range: -5.0154
Max Act: 4.7653. Min Act: -0.1700
Data Index: 6248218 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0154. Min Range: -5.0154
Max Act: 4.7653. Min Act: -0.1700
Data Index: 1797525 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0154. Min Range: -5.0154
Max Act: 4.6716. Min Act: -0.1700
Data Index: 7672918 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0154. Min Range: -5.0154
Max Act: 4.6716. Min Act: -0.1700
Data Index: 2766303 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0154. Min Range: -5.0154
Max Act: 4.6716. Min Act: -0.1700
Data Index: 4257366 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0154. Min Range: -5.0154
Max Act: 4.6716. Min Act: -0.1700
Data Index: 5994393 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0154. Min Range: -5.0154
Max Act: 4.6091. Min Act: -0.1700
Data Index: 192761 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0154. Min Range: -5.0154
Max Act: 4.6403. Min Act: -0.1700
Data Index: 8789425 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0154. Min Range: -5.0154
Max Act: 4.6403. Min Act: -0.1700
Data Index: 5055192 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0154. Min Range: -5.0154
Max Act: 4.5778. Min Act: -0.1700
Data Index: 8180314 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0154. Min Range: -5.0154
Max Act: 4.5778. Min Act: -0.1700
Data Index: 1728415 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0154. Min Range: -5.0154
Max Act: 4.6091. Min Act: -0.1700
Data Index: 5537105 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0154. Min Range: -5.0154
Max Act: 4.5778. Min Act: -0.1700
Data Index: 6001916 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0154. Min Range: -5.0154
Max Act: 4.5778. Min Act: -0.1700
Data Index: 3553538 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0154. Min Range: -5.0154
Max Act: 4.5466. Min Act: -0.1700
Data Index: 2271831 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0154. Min Range: -5.0154
Max Act: 4.5778. Min Act: -0.1700
Data Index: 5376185 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0154. Min Range: -5.0154
Max Act: 4.5466. Min Act: -0.1700
Data Index: 7677478 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0154. Min Range: -5.0154
Max Act: 4.5153. Min Act: -0.1700
Data Index: 4281263 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0154. Min Range: -5.0154
Max Act: 4.5153. Min Act: -0.1700
Data Index: 5749887 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #19