Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4564 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7964. Min Range: -4.7964
Max Act: 4.7964. Min Act: -0.1700
Data Index: 1677512 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7964. Min Range: -4.7964
Max Act: 4.7651. Min Act: -0.1700
Data Index: 2623471 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7964. Min Range: -4.7964
Max Act: 4.7651. Min Act: -0.1700
Data Index: 885649 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7964. Min Range: -4.7964
Max Act: 4.7026. Min Act: -0.1700
Data Index: 1840463 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7964. Min Range: -4.7964
Max Act: 4.6401. Min Act: -0.1700
Data Index: 4928109 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7964. Min Range: -4.7964
Max Act: 4.6401. Min Act: -0.1700
Data Index: 5485046 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7964. Min Range: -4.7964
Max Act: 4.5776. Min Act: -0.1700
Data Index: 8532447 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7964. Min Range: -4.7964
Max Act: 4.6089. Min Act: -0.1700
Data Index: 5361286 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7964. Min Range: -4.7964
Max Act: 4.6089. Min Act: -0.1700
Data Index: 1037774 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7964. Min Range: -4.7964
Max Act: 4.5776. Min Act: -0.1700
Data Index: 1550924 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7964. Min Range: -4.7964
Max Act: 4.5151. Min Act: -0.1700
Data Index: 1710034 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7964. Min Range: -4.7964
Max Act: 4.5464. Min Act: -0.1700
Data Index: 3322350 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7964. Min Range: -4.7964
Max Act: 4.5151. Min Act: -0.1700
Data Index: 5597593 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7964. Min Range: -4.7964
Max Act: 4.5151. Min Act: -0.1700
Data Index: 8535917 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7964. Min Range: -4.7964
Max Act: 4.5151. Min Act: -0.1700
Data Index: 58707 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7964. Min Range: -4.7964
Max Act: 4.4839. Min Act: -0.1700
Data Index: 748869 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7964. Min Range: -4.7964
Max Act: 4.4839. Min Act: -0.1700
Data Index: 5559145 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7964. Min Range: -4.7964
Max Act: 4.4839. Min Act: -0.1700
Data Index: 4743844 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7964. Min Range: -4.7964
Max Act: 4.4839. Min Act: -0.1700
Data Index: 7262182 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7964. Min Range: -4.7964
Max Act: 4.4839. Min Act: -0.1700
Data Index: 2020171 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19