Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 28 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1144. Min Range: -6.1144
Max Act: 6.1144. Min Act: -0.1700
Data Index: 3114359 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1144. Min Range: -6.1144
Max Act: 6.0519. Min Act: -0.1700
Data Index: 7850755 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1144. Min Range: -6.1144
Max Act: 5.9269. Min Act: -0.1700
Data Index: 4771981 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1144. Min Range: -6.1144
Max Act: 5.8957. Min Act: -0.1700
Data Index: 8117011 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1144. Min Range: -6.1144
Max Act: 5.8957. Min Act: -0.1700
Data Index: 7022665 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1144. Min Range: -6.1144
Max Act: 5.8644. Min Act: -0.1700
Data Index: 3324430 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1144. Min Range: -6.1144
Max Act: 5.8332. Min Act: -0.1700
Data Index: 6990024 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1144. Min Range: -6.1144
Max Act: 5.8644. Min Act: -0.1700
Data Index: 6966743 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1144. Min Range: -6.1144
Max Act: 5.8644. Min Act: -0.1700
Data Index: 6869413 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1144. Min Range: -6.1144
Max Act: 5.8644. Min Act: -0.1700
Data Index: 5784654 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1144. Min Range: -6.1144
Max Act: 5.8644. Min Act: -0.1700
Data Index: 5284760 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1144. Min Range: -6.1144
Max Act: 5.8644. Min Act: -0.1700
Data Index: 4311371 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1144. Min Range: -6.1144
Max Act: 5.8644. Min Act: -0.1700
Data Index: 4311373 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1144. Min Range: -6.1144
Max Act: 5.8332. Min Act: -0.1700
Data Index: 4161496 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1144. Min Range: -6.1144
Max Act: 5.8644. Min Act: -0.1700
Data Index: 4161500 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1144. Min Range: -6.1144
Max Act: 5.8332. Min Act: -0.1700
Data Index: 3840253 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1144. Min Range: -6.1144
Max Act: 5.8644. Min Act: -0.1700
Data Index: 3156877 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1144. Min Range: -6.1144
Max Act: 5.8644. Min Act: -0.1700
Data Index: 2475607 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1144. Min Range: -6.1144
Max Act: 5.8644. Min Act: -0.1700
Data Index: 2296123 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1144. Min Range: -6.1144
Max Act: 5.8644. Min Act: -0.1700
Data Index: 1314802 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #19