Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2599 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1807. Min Range: -8.1807
Max Act: 8.1807. Min Act: -0.1700
Data Index: 5255902 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1807. Min Range: -8.1807
Max Act: 8.0870. Min Act: -0.1700
Data Index: 1346747 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1807. Min Range: -8.1807
Max Act: 8.0245. Min Act: -0.1700
Data Index: 4516712 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1807. Min Range: -8.1807
Max Act: 7.9932. Min Act: -0.1700
Data Index: 7998327 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1807. Min Range: -8.1807
Max Act: 7.9620. Min Act: -0.1700
Data Index: 8162366 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1807. Min Range: -8.1807
Max Act: 7.9620. Min Act: -0.1700
Data Index: 2411627 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1807. Min Range: -8.1807
Max Act: 7.7745. Min Act: -0.1700
Data Index: 8588635 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1807. Min Range: -8.1807
Max Act: 7.7120. Min Act: -0.1700
Data Index: 4300260 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1807. Min Range: -8.1807
Max Act: 7.7120. Min Act: -0.1700
Data Index: 4787164 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1807. Min Range: -8.1807
Max Act: 7.7120. Min Act: -0.1700
Data Index: 3603670 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1807. Min Range: -8.1807
Max Act: 7.7120. Min Act: -0.1700
Data Index: 8304215 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1807. Min Range: -8.1807
Max Act: 7.6807. Min Act: -0.1700
Data Index: 2393393 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1807. Min Range: -8.1807
Max Act: 7.6495. Min Act: -0.1700
Data Index: 1142698 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1807. Min Range: -8.1807
Max Act: 7.6182. Min Act: -0.1700
Data Index: 1895035 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1807. Min Range: -8.1807
Max Act: 7.6182. Min Act: -0.1700
Data Index: 687414 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1807. Min Range: -8.1807
Max Act: 7.5870. Min Act: -0.1700
Data Index: 1774164 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1807. Min Range: -8.1807
Max Act: 7.6182. Min Act: -0.1700
Data Index: 2900102 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1807. Min Range: -8.1807
Max Act: 7.5557. Min Act: -0.1700
Data Index: 6537084 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1807. Min Range: -8.1807
Max Act: 7.5245. Min Act: -0.1700
Data Index: 3500408 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1807. Min Range: -8.1807
Max Act: 7.4932. Min Act: -0.1700
Data Index: 6366777 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #19