Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2898 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8673. Min Range: -3.8673
Max Act: 3.8361. Min Act: -0.1700
Data Index: 4915518 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8673. Min Range: -3.8673
Max Act: 3.8673. Min Act: -0.1700
Data Index: 1899638 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8673. Min Range: -3.8673
Max Act: 3.8048. Min Act: -0.1700
Data Index: 8434867 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8673. Min Range: -3.8673
Max Act: 3.7579. Min Act: -0.1700
Data Index: 4833444 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8673. Min Range: -3.8673
Max Act: 3.7579. Min Act: -0.1700
Data Index: 1696820 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8673. Min Range: -3.8673
Max Act: 3.7735. Min Act: -0.1700
Data Index: 3315146 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8673. Min Range: -3.8673
Max Act: 3.6797. Min Act: -0.1700
Data Index: 1291551 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8673. Min Range: -3.8673
Max Act: 3.6797. Min Act: -0.1700
Data Index: 3239757 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8673. Min Range: -3.8673
Max Act: 3.6797. Min Act: -0.1700
Data Index: 5354344 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8673. Min Range: -3.8673
Max Act: 3.6640. Min Act: -0.1700
Data Index: 6583163 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8673. Min Range: -3.8673
Max Act: 3.6327. Min Act: -0.1700
Data Index: 6867088 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8673. Min Range: -3.8673
Max Act: 3.6640. Min Act: -0.1700
Data Index: 1290136 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8673. Min Range: -3.8673
Max Act: 3.6484. Min Act: -0.1700
Data Index: 2580962 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8673. Min Range: -3.8673
Max Act: 3.6484. Min Act: -0.1700
Data Index: 3557341 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8673. Min Range: -3.8673
Max Act: 3.6327. Min Act: -0.1700
Data Index: 3261189 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8673. Min Range: -3.8673
Max Act: 3.6171. Min Act: -0.1700
Data Index: 6494866 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8673. Min Range: -3.8673
Max Act: 3.6014. Min Act: -0.1700
Data Index: 6109172 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8673. Min Range: -3.8673
Max Act: 3.6014. Min Act: -0.1700
Data Index: 5653540 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8673. Min Range: -3.8673
Max Act: 3.6014. Min Act: -0.1700
Data Index: 4863359 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8673. Min Range: -3.8673
Max Act: 3.5858. Min Act: -0.1700
Data Index: 5735859 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #19