Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3966 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0512. Min Range: -7.0512
Max Act: 7.0512. Min Act: -0.1700
Data Index: 3062093 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0512. Min Range: -7.0512
Max Act: 6.9262. Min Act: -0.1700
Data Index: 5507008 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0512. Min Range: -7.0512
Max Act: 6.8949. Min Act: -0.1700
Data Index: 341942 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0512. Min Range: -7.0512
Max Act: 6.8949. Min Act: -0.1700
Data Index: 4486364 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0512. Min Range: -7.0512
Max Act: 6.8637. Min Act: -0.1700
Data Index: 7789941 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0512. Min Range: -7.0512
Max Act: 6.7699. Min Act: -0.1700
Data Index: 2340804 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0512. Min Range: -7.0512
Max Act: 6.7387. Min Act: -0.1700
Data Index: 1204069 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0512. Min Range: -7.0512
Max Act: 6.7074. Min Act: -0.1700
Data Index: 70876 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0512. Min Range: -7.0512
Max Act: 6.7074. Min Act: -0.1700
Data Index: 866166 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0512. Min Range: -7.0512
Max Act: 6.7074. Min Act: -0.1700
Data Index: 8164832 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0512. Min Range: -7.0512
Max Act: 6.6137. Min Act: -0.1700
Data Index: 70871 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0512. Min Range: -7.0512
Max Act: 6.6137. Min Act: -0.1700
Data Index: 7704171 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0512. Min Range: -7.0512
Max Act: 6.6449. Min Act: -0.1700
Data Index: 5713708 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0512. Min Range: -7.0512
Max Act: 6.5512. Min Act: -0.1700
Data Index: 7566825 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0512. Min Range: -7.0512
Max Act: 6.5512. Min Act: -0.1700
Data Index: 3821336 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0512. Min Range: -7.0512
Max Act: 6.5824. Min Act: -0.1700
Data Index: 7025551 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0512. Min Range: -7.0512
Max Act: 6.5512. Min Act: -0.1700
Data Index: 4131932 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0512. Min Range: -7.0512
Max Act: 6.5512. Min Act: -0.1700
Data Index: 2003205 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0512. Min Range: -7.0512
Max Act: 6.5512. Min Act: -0.1700
Data Index: 3142877 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0512. Min Range: -7.0512
Max Act: 6.5512. Min Act: -0.1700
Data Index: 1698192 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #19