Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3554 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0144. Min Range: -5.0144
Max Act: 5.0144. Min Act: -0.1700
Data Index: 963329 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0144. Min Range: -5.0144
Max Act: 4.9519. Min Act: -0.1700
Data Index: 1572094 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0144. Min Range: -5.0144
Max Act: 4.9519. Min Act: -0.1700
Data Index: 1427406 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0144. Min Range: -5.0144
Max Act: 4.8894. Min Act: -0.1700
Data Index: 228497 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0144. Min Range: -5.0144
Max Act: 4.8894. Min Act: -0.1700
Data Index: 1345071 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0144. Min Range: -5.0144
Max Act: 4.8581. Min Act: -0.1700
Data Index: 5955264 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0144. Min Range: -5.0144
Max Act: 4.7956. Min Act: -0.1700
Data Index: 6917454 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0144. Min Range: -5.0144
Max Act: 4.7956. Min Act: -0.1700
Data Index: 8280671 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0144. Min Range: -5.0144
Max Act: 4.7331. Min Act: -0.1700
Data Index: 6527872 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0144. Min Range: -5.0144
Max Act: 4.7331. Min Act: -0.1700
Data Index: 3995039 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0144. Min Range: -5.0144
Max Act: 4.7019. Min Act: -0.1700
Data Index: 2530293 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0144. Min Range: -5.0144
Max Act: 4.7019. Min Act: -0.1700
Data Index: 540338 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0144. Min Range: -5.0144
Max Act: 4.7019. Min Act: -0.1700
Data Index: 5563539 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0144. Min Range: -5.0144
Max Act: 4.6394. Min Act: -0.1700
Data Index: 108189 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0144. Min Range: -5.0144
Max Act: 4.6706. Min Act: -0.1700
Data Index: 1934719 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0144. Min Range: -5.0144
Max Act: 4.6394. Min Act: -0.1700
Data Index: 5072123 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0144. Min Range: -5.0144
Max Act: 4.6706. Min Act: -0.1700
Data Index: 5058765 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0144. Min Range: -5.0144
Max Act: 4.6394. Min Act: -0.1700
Data Index: 6841343 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0144. Min Range: -5.0144
Max Act: 4.6394. Min Act: -0.1700
Data Index: 7778933 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0144. Min Range: -5.0144
Max Act: 4.6081. Min Act: -0.1700
Data Index: 6620177 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #19