Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2165 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8133. Min Range: -6.8133
Max Act: 6.8133. Min Act: -0.1700
Data Index: 5710272 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8133. Min Range: -6.8133
Max Act: 6.6258. Min Act: -0.1700
Data Index: 4216740 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8133. Min Range: -6.8133
Max Act: 6.6258. Min Act: -0.1700
Data Index: 5112542 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8133. Min Range: -6.8133
Max Act: 6.5008. Min Act: -0.1700
Data Index: 2804031 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8133. Min Range: -6.8133
Max Act: 6.4695. Min Act: -0.1700
Data Index: 1719958 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8133. Min Range: -6.8133
Max Act: 6.4695. Min Act: -0.1700
Data Index: 5506619 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8133. Min Range: -6.8133
Max Act: 6.4383. Min Act: -0.1700
Data Index: 2846113 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8133. Min Range: -6.8133
Max Act: 6.4070. Min Act: -0.1700
Data Index: 5320780 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8133. Min Range: -6.8133
Max Act: 6.4070. Min Act: -0.1700
Data Index: 6484840 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8133. Min Range: -6.8133
Max Act: 6.3758. Min Act: -0.1700
Data Index: 3975375 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8133. Min Range: -6.8133
Max Act: 6.4070. Min Act: -0.1700
Data Index: 6721768 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8133. Min Range: -6.8133
Max Act: 6.4070. Min Act: -0.1700
Data Index: 7335427 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8133. Min Range: -6.8133
Max Act: 6.3758. Min Act: -0.1700
Data Index: 3802782 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8133. Min Range: -6.8133
Max Act: 6.3758. Min Act: -0.1700
Data Index: 549039 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8133. Min Range: -6.8133
Max Act: 6.3758. Min Act: -0.1700
Data Index: 8419390 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8133. Min Range: -6.8133
Max Act: 6.3758. Min Act: -0.1700
Data Index: 7877655 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8133. Min Range: -6.8133
Max Act: 6.3758. Min Act: -0.1700
Data Index: 5526685 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8133. Min Range: -6.8133
Max Act: 6.4070. Min Act: -0.1700
Data Index: 6311205 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8133. Min Range: -6.8133
Max Act: 6.3758. Min Act: -0.1700
Data Index: 3571396 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8133. Min Range: -6.8133
Max Act: 6.3445. Min Act: -0.1700
Data Index: 5782098 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #19