Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3134 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8793. Min Range: -5.8793
Max Act: 5.8793. Min Act: -0.1700
Data Index: 4585373 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8793. Min Range: -5.8793
Max Act: 5.8793. Min Act: -0.1700
Data Index: 4727121 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8793. Min Range: -5.8793
Max Act: 5.8480. Min Act: -0.1700
Data Index: 6835137 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8793. Min Range: -5.8793
Max Act: 5.7855. Min Act: -0.1700
Data Index: 8431845 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8793. Min Range: -5.8793
Max Act: 5.7543. Min Act: -0.1700
Data Index: 642094 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8793. Min Range: -5.8793
Max Act: 5.7543. Min Act: -0.1700
Data Index: 6812022 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8793. Min Range: -5.8793
Max Act: 5.6918. Min Act: -0.1700
Data Index: 8113749 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8793. Min Range: -5.8793
Max Act: 5.6918. Min Act: -0.1700
Data Index: 3503847 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8793. Min Range: -5.8793
Max Act: 5.6918. Min Act: -0.1700
Data Index: 4727124 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8793. Min Range: -5.8793
Max Act: 5.6918. Min Act: -0.1700
Data Index: 7197743 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8793. Min Range: -5.8793
Max Act: 5.6918. Min Act: -0.1700
Data Index: 4713794 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8793. Min Range: -5.8793
Max Act: 5.6605. Min Act: -0.1700
Data Index: 432051 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8793. Min Range: -5.8793
Max Act: 5.6605. Min Act: -0.1700
Data Index: 1848350 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8793. Min Range: -5.8793
Max Act: 5.6918. Min Act: -0.1700
Data Index: 6835136 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8793. Min Range: -5.8793
Max Act: 5.6293. Min Act: -0.1700
Data Index: 5740990 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8793. Min Range: -5.8793
Max Act: 5.6293. Min Act: -0.1700
Data Index: 5001876 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8793. Min Range: -5.8793
Max Act: 5.5668. Min Act: -0.1700
Data Index: 1228588 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8793. Min Range: -5.8793
Max Act: 5.5980. Min Act: -0.1700
Data Index: 6812028 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8793. Min Range: -5.8793
Max Act: 5.5668. Min Act: -0.1700
Data Index: 1308521 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8793. Min Range: -5.8793
Max Act: 5.5355. Min Act: -0.1700
Data Index: 8113745 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #19