Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5528 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6118. Min Range: -5.6118
Max Act: 5.6118. Min Act: -0.1700
Data Index: 4882563 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6118. Min Range: -5.6118
Max Act: 5.5180. Min Act: -0.1700
Data Index: 110743 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6118. Min Range: -5.6118
Max Act: 5.4555. Min Act: -0.1700
Data Index: 155632 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6118. Min Range: -5.6118
Max Act: 5.4243. Min Act: -0.1700
Data Index: 5255831 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6118. Min Range: -5.6118
Max Act: 5.4243. Min Act: -0.1700
Data Index: 1436940 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6118. Min Range: -5.6118
Max Act: 5.4243. Min Act: -0.1700
Data Index: 8119303 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6118. Min Range: -5.6118
Max Act: 5.3930. Min Act: -0.1700
Data Index: 1789442 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6118. Min Range: -5.6118
Max Act: 5.3930. Min Act: -0.1700
Data Index: 2032490 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6118. Min Range: -5.6118
Max Act: 5.3930. Min Act: -0.1700
Data Index: 8382328 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6118. Min Range: -5.6118
Max Act: 5.3930. Min Act: -0.1700
Data Index: 2032491 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6118. Min Range: -5.6118
Max Act: 5.3930. Min Act: -0.1700
Data Index: 781754 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6118. Min Range: -5.6118
Max Act: 5.3930. Min Act: -0.1700
Data Index: 287519 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6118. Min Range: -5.6118
Max Act: 5.3930. Min Act: -0.1700
Data Index: 6753038 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6118. Min Range: -5.6118
Max Act: 5.3930. Min Act: -0.1700
Data Index: 3194707 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6118. Min Range: -5.6118
Max Act: 5.3930. Min Act: -0.1700
Data Index: 2623012 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6118. Min Range: -5.6118
Max Act: 5.3618. Min Act: -0.1700
Data Index: 6989234 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6118. Min Range: -5.6118
Max Act: 5.3618. Min Act: -0.1700
Data Index: 7203164 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6118. Min Range: -5.6118
Max Act: 5.3618. Min Act: -0.1700
Data Index: 7224271 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6118. Min Range: -5.6118
Max Act: 5.3618. Min Act: -0.1700
Data Index: 4110975 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6118. Min Range: -5.6118
Max Act: 5.3618. Min Act: -0.1700
Data Index: 7564866 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #19