Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3155 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4156. Min Range: -7.4156
Max Act: 7.3844. Min Act: -0.1700
Data Index: 6815204 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4156. Min Range: -7.4156
Max Act: 7.4156. Min Act: -0.1700
Data Index: 8230680 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4156. Min Range: -7.4156
Max Act: 7.4156. Min Act: -0.1700
Data Index: 2703761 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4156. Min Range: -7.4156
Max Act: 7.2906. Min Act: -0.1700
Data Index: 4868118 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4156. Min Range: -7.4156
Max Act: 7.2594. Min Act: -0.1700
Data Index: 5008648 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4156. Min Range: -7.4156
Max Act: 7.1344. Min Act: -0.1700
Data Index: 1058778 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4156. Min Range: -7.4156
Max Act: 7.1031. Min Act: -0.1700
Data Index: 5917689 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4156. Min Range: -7.4156
Max Act: 7.1031. Min Act: -0.1700
Data Index: 1358725 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4156. Min Range: -7.4156
Max Act: 7.0094. Min Act: -0.1700
Data Index: 2677225 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4156. Min Range: -7.4156
Max Act: 7.0094. Min Act: -0.1700
Data Index: 338413 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4156. Min Range: -7.4156
Max Act: 6.9781. Min Act: -0.1700
Data Index: 8125956 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4156. Min Range: -7.4156
Max Act: 6.9469. Min Act: -0.1700
Data Index: 8741418 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4156. Min Range: -7.4156
Max Act: 6.8844. Min Act: -0.1700
Data Index: 8534844 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4156. Min Range: -7.4156
Max Act: 6.8531. Min Act: -0.1700
Data Index: 2604446 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4156. Min Range: -7.4156
Max Act: 6.8531. Min Act: -0.1700
Data Index: 5298639 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4156. Min Range: -7.4156
Max Act: 6.8531. Min Act: -0.1700
Data Index: 8700542 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4156. Min Range: -7.4156
Max Act: 6.8219. Min Act: -0.1700
Data Index: 7217367 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4156. Min Range: -7.4156
Max Act: 6.8219. Min Act: -0.1700
Data Index: 3314075 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4156. Min Range: -7.4156
Max Act: 6.7906. Min Act: -0.1700
Data Index: 733289 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4156. Min Range: -7.4156
Max Act: 6.7906. Min Act: -0.1700
Data Index: 703158 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #19