Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3131 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2821. Min Range: -7.2821
Max Act: 7.2821. Min Act: -0.1700
Data Index: 4336465 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2821. Min Range: -7.2821
Max Act: 6.9071. Min Act: -0.1700
Data Index: 2088175 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2821. Min Range: -7.2821
Max Act: 6.8758. Min Act: -0.1700
Data Index: 6058125 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2821. Min Range: -7.2821
Max Act: 6.8133. Min Act: -0.1700
Data Index: 2005999 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2821. Min Range: -7.2821
Max Act: 6.7508. Min Act: -0.1700
Data Index: 2238510 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2821. Min Range: -7.2821
Max Act: 6.6258. Min Act: -0.1700
Data Index: 6443939 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2821. Min Range: -7.2821
Max Act: 6.5633. Min Act: -0.1700
Data Index: 3282740 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2821. Min Range: -7.2821
Max Act: 6.5008. Min Act: -0.1700
Data Index: 4034304 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2821. Min Range: -7.2821
Max Act: 6.5008. Min Act: -0.1700
Data Index: 2699041 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2821. Min Range: -7.2821
Max Act: 6.4383. Min Act: -0.1700
Data Index: 1926196 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2821. Min Range: -7.2821
Max Act: 6.4071. Min Act: -0.1700
Data Index: 1827831 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2821. Min Range: -7.2821
Max Act: 6.4071. Min Act: -0.1700
Data Index: 411618 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2821. Min Range: -7.2821
Max Act: 6.3758. Min Act: -0.1700
Data Index: 7400657 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2821. Min Range: -7.2821
Max Act: 6.3758. Min Act: -0.1700
Data Index: 3254493 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2821. Min Range: -7.2821
Max Act: 6.3133. Min Act: -0.1700
Data Index: 5681003 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2821. Min Range: -7.2821
Max Act: 6.3446. Min Act: -0.1700
Data Index: 806469 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2821. Min Range: -7.2821
Max Act: 6.3758. Min Act: -0.1700
Data Index: 4048609 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2821. Min Range: -7.2821
Max Act: 6.3133. Min Act: -0.1700
Data Index: 3215715 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2821. Min Range: -7.2821
Max Act: 6.3133. Min Act: -0.1700
Data Index: 8468172 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2821. Min Range: -7.2821
Max Act: 6.2821. Min Act: -0.1700
Data Index: 5837955 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #19