Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2156 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6106. Min Range: -6.6106
Max Act: 6.6106. Min Act: -0.1700
Data Index: 154899 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6106. Min Range: -6.6106
Max Act: 6.5793. Min Act: -0.1700
Data Index: 8438948 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6106. Min Range: -6.6106
Max Act: 6.5793. Min Act: -0.1700
Data Index: 1804280 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6106. Min Range: -6.6106
Max Act: 6.5793. Min Act: -0.1700
Data Index: 2286511 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6106. Min Range: -6.6106
Max Act: 6.5481. Min Act: -0.1700
Data Index: 3586710 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6106. Min Range: -6.6106
Max Act: 6.5481. Min Act: -0.1700
Data Index: 3060488 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6106. Min Range: -6.6106
Max Act: 6.5481. Min Act: -0.1700
Data Index: 1232883 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6106. Min Range: -6.6106
Max Act: 6.5168. Min Act: -0.1700
Data Index: 5950058 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6106. Min Range: -6.6106
Max Act: 6.5168. Min Act: -0.1700
Data Index: 1823995 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6106. Min Range: -6.6106
Max Act: 6.5168. Min Act: -0.1700
Data Index: 3664805 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6106. Min Range: -6.6106
Max Act: 6.5168. Min Act: -0.1700
Data Index: 8091326 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6106. Min Range: -6.6106
Max Act: 6.4856. Min Act: -0.1700
Data Index: 1522942 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6106. Min Range: -6.6106
Max Act: 6.4856. Min Act: -0.1700
Data Index: 1060473 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6106. Min Range: -6.6106
Max Act: 6.4856. Min Act: -0.1700
Data Index: 3634179 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6106. Min Range: -6.6106
Max Act: 6.4856. Min Act: -0.1700
Data Index: 3586711 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6106. Min Range: -6.6106
Max Act: 6.4856. Min Act: -0.1700
Data Index: 5624474 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6106. Min Range: -6.6106
Max Act: 6.4543. Min Act: -0.1700
Data Index: 2688 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6106. Min Range: -6.6106
Max Act: 6.4543. Min Act: -0.1700
Data Index: 6222130 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6106. Min Range: -6.6106
Max Act: 6.4543. Min Act: -0.1700
Data Index: 6421821 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6106. Min Range: -6.6106
Max Act: 6.4543. Min Act: -0.1700
Data Index: 5007078 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #19