Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6153 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1591. Min Range: -6.1591
Max Act: 6.1591. Min Act: -0.1700
Data Index: 4899976 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1591. Min Range: -6.1591
Max Act: 6.0341. Min Act: -0.1700
Data Index: 477421 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1591. Min Range: -6.1591
Max Act: 5.9091. Min Act: -0.1700
Data Index: 2556442 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1591. Min Range: -6.1591
Max Act: 5.5028. Min Act: -0.1700
Data Index: 2077240 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1591. Min Range: -6.1591
Max Act: 5.5341. Min Act: -0.1700
Data Index: 7660417 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1591. Min Range: -6.1591
Max Act: 5.4091. Min Act: -0.1700
Data Index: 5886123 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1591. Min Range: -6.1591
Max Act: 5.3466. Min Act: -0.1700
Data Index: 4882896 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1591. Min Range: -6.1591
Max Act: 5.4091. Min Act: -0.1700
Data Index: 4121928 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1591. Min Range: -6.1591
Max Act: 5.3153. Min Act: -0.1700
Data Index: 8121274 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1591. Min Range: -6.1591
Max Act: 5.3153. Min Act: -0.1700
Data Index: 1546183 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1591. Min Range: -6.1591
Max Act: 5.3466. Min Act: -0.1700
Data Index: 5274965 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1591. Min Range: -6.1591
Max Act: 5.3153. Min Act: -0.1700
Data Index: 4768484 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1591. Min Range: -6.1591
Max Act: 5.3153. Min Act: -0.1700
Data Index: 4233935 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1591. Min Range: -6.1591
Max Act: 5.2841. Min Act: -0.1700
Data Index: 545129 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1591. Min Range: -6.1591
Max Act: 5.3153. Min Act: -0.1700
Data Index: 1008096 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1591. Min Range: -6.1591
Max Act: 5.2841. Min Act: -0.1700
Data Index: 6318013 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1591. Min Range: -6.1591
Max Act: 5.2841. Min Act: -0.1700
Data Index: 839048 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1591. Min Range: -6.1591
Max Act: 5.2528. Min Act: -0.1700
Data Index: 5733432 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1591. Min Range: -6.1591
Max Act: 5.2528. Min Act: -0.1700
Data Index: 6912065 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1591. Min Range: -6.1591
Max Act: 5.2528. Min Act: -0.1700
Data Index: 3790598 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #19