Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1313 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7644. Min Range: -6.7644
Max Act: 6.7644. Min Act: -0.1700
Data Index: 6453038 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7644. Min Range: -6.7644
Max Act: 6.2644. Min Act: -0.1700
Data Index: 5001044 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7644. Min Range: -6.7644
Max Act: 6.2019. Min Act: -0.1700
Data Index: 4362566 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7644. Min Range: -6.7644
Max Act: 6.1706. Min Act: -0.1700
Data Index: 7843432 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7644. Min Range: -6.7644
Max Act: 6.1394. Min Act: -0.1700
Data Index: 101789 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7644. Min Range: -6.7644
Max Act: 6.1081. Min Act: -0.1700
Data Index: 4221141 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7644. Min Range: -6.7644
Max Act: 6.1081. Min Act: -0.1700
Data Index: 3225923 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7644. Min Range: -6.7644
Max Act: 6.1081. Min Act: -0.1700
Data Index: 5413848 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7644. Min Range: -6.7644
Max Act: 6.1081. Min Act: -0.1700
Data Index: 2400639 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7644. Min Range: -6.7644
Max Act: 6.1081. Min Act: -0.1700
Data Index: 3434112 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7644. Min Range: -6.7644
Max Act: 6.0456. Min Act: -0.1700
Data Index: 6476386 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7644. Min Range: -6.7644
Max Act: 6.0456. Min Act: -0.1700
Data Index: 5787371 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7644. Min Range: -6.7644
Max Act: 6.0456. Min Act: -0.1700
Data Index: 1712518 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7644. Min Range: -6.7644
Max Act: 5.9831. Min Act: -0.1700
Data Index: 6514265 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7644. Min Range: -6.7644
Max Act: 5.9831. Min Act: -0.1700
Data Index: 1834150 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7644. Min Range: -6.7644
Max Act: 5.9831. Min Act: -0.1700
Data Index: 6945883 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7644. Min Range: -6.7644
Max Act: 6.0144. Min Act: -0.1700
Data Index: 8115698 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7644. Min Range: -6.7644
Max Act: 5.9519. Min Act: -0.1700
Data Index: 5068801 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7644. Min Range: -6.7644
Max Act: 5.9206. Min Act: -0.1700
Data Index: 5664576 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7644. Min Range: -6.7644
Max Act: 5.9519. Min Act: -0.1700
Data Index: 5413849 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #19