Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2438 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9092. Min Range: -4.9092
Max Act: 4.9092. Min Act: -0.1700
Data Index: 6551746 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9092. Min Range: -4.9092
Max Act: 4.8467. Min Act: -0.1700
Data Index: 6368678 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9092. Min Range: -4.9092
Max Act: 4.8467. Min Act: -0.1700
Data Index: 4104689 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9092. Min Range: -4.9092
Max Act: 4.7842. Min Act: -0.1700
Data Index: 7812061 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9092. Min Range: -4.9092
Max Act: 4.7842. Min Act: -0.1700
Data Index: 3736289 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9092. Min Range: -4.9092
Max Act: 4.7529. Min Act: -0.1700
Data Index: 6612851 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9092. Min Range: -4.9092
Max Act: 4.7529. Min Act: -0.1700
Data Index: 2650666 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9092. Min Range: -4.9092
Max Act: 4.7217. Min Act: -0.1700
Data Index: 7981135 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9092. Min Range: -4.9092
Max Act: 4.6904. Min Act: -0.1700
Data Index: 4401721 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9092. Min Range: -4.9092
Max Act: 4.7217. Min Act: -0.1700
Data Index: 8234635 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9092. Min Range: -4.9092
Max Act: 4.7217. Min Act: -0.1700
Data Index: 1915136 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9092. Min Range: -4.9092
Max Act: 4.7217. Min Act: -0.1700
Data Index: 1103512 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9092. Min Range: -4.9092
Max Act: 4.7217. Min Act: -0.1700
Data Index: 5778802 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9092. Min Range: -4.9092
Max Act: 4.7217. Min Act: -0.1700
Data Index: 8685469 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9092. Min Range: -4.9092
Max Act: 4.6904. Min Act: -0.1700
Data Index: 3834039 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9092. Min Range: -4.9092
Max Act: 4.6904. Min Act: -0.1700
Data Index: 4356205 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9092. Min Range: -4.9092
Max Act: 4.6904. Min Act: -0.1700
Data Index: 8335930 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9092. Min Range: -4.9092
Max Act: 4.6904. Min Act: -0.1700
Data Index: 904602 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9092. Min Range: -4.9092
Max Act: 4.6904. Min Act: -0.1700
Data Index: 7378584 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9092. Min Range: -4.9092
Max Act: 4.6904. Min Act: -0.1700
Data Index: 2861690 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #19