Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2506 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1967. Min Range: -8.1967
Max Act: 8.1967. Min Act: -0.1700
Data Index: 915412 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1967. Min Range: -8.1967
Max Act: 8.1967. Min Act: -0.1700
Data Index: 3822275 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1967. Min Range: -8.1967
Max Act: 8.0717. Min Act: -0.1700
Data Index: 3128998 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1967. Min Range: -8.1967
Max Act: 8.0092. Min Act: -0.1700
Data Index: 277622 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1967. Min Range: -8.1967
Max Act: 8.0092. Min Act: -0.1700
Data Index: 5906882 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1967. Min Range: -8.1967
Max Act: 8.0092. Min Act: -0.1700
Data Index: 2640063 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1967. Min Range: -8.1967
Max Act: 8.0092. Min Act: -0.1700
Data Index: 5934829 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1967. Min Range: -8.1967
Max Act: 7.9467. Min Act: -0.1700
Data Index: 6902530 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1967. Min Range: -8.1967
Max Act: 7.9467. Min Act: -0.1700
Data Index: 4860964 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1967. Min Range: -8.1967
Max Act: 7.9467. Min Act: -0.1700
Data Index: 385637 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1967. Min Range: -8.1967
Max Act: 8.0092. Min Act: -0.1700
Data Index: 6296146 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1967. Min Range: -8.1967
Max Act: 7.9467. Min Act: -0.1700
Data Index: 902498 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1967. Min Range: -8.1967
Max Act: 7.8842. Min Act: -0.1700
Data Index: 5157541 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1967. Min Range: -8.1967
Max Act: 7.9467. Min Act: -0.1700
Data Index: 6702789 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1967. Min Range: -8.1967
Max Act: 7.8842. Min Act: -0.1700
Data Index: 4575857 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1967. Min Range: -8.1967
Max Act: 7.8842. Min Act: -0.1700
Data Index: 4043865 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1967. Min Range: -8.1967
Max Act: 7.8217. Min Act: -0.1700
Data Index: 6751669 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1967. Min Range: -8.1967
Max Act: 7.8217. Min Act: -0.1700
Data Index: 5154685 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1967. Min Range: -8.1967
Max Act: 7.8217. Min Act: -0.1700
Data Index: 6443567 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1967. Min Range: -8.1967
Max Act: 7.8217. Min Act: -0.1700
Data Index: 6172356 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19