Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 534 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6558. Min Range: -5.6558
Max Act: 5.6558. Min Act: -0.1700
Data Index: 8289116 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6558. Min Range: -5.6558
Max Act: 5.2183. Min Act: -0.1700
Data Index: 1747563 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6558. Min Range: -5.6558
Max Act: 5.0933. Min Act: -0.1700
Data Index: 8289120 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6558. Min Range: -5.6558
Max Act: 5.0308. Min Act: -0.1700
Data Index: 3361993 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6558. Min Range: -5.6558
Max Act: 4.9370. Min Act: -0.1700
Data Index: 1441115 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6558. Min Range: -5.6558
Max Act: 4.9058. Min Act: -0.1700
Data Index: 1764310 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6558. Min Range: -5.6558
Max Act: 4.8745. Min Act: -0.1700
Data Index: 8352130 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6558. Min Range: -5.6558
Max Act: 4.8433. Min Act: -0.1700
Data Index: 4412854 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6558. Min Range: -5.6558
Max Act: 4.8433. Min Act: -0.1700
Data Index: 8059274 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6558. Min Range: -5.6558
Max Act: 4.8120. Min Act: -0.1700
Data Index: 6499154 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6558. Min Range: -5.6558
Max Act: 4.7808. Min Act: -0.1700
Data Index: 139527 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6558. Min Range: -5.6558
Max Act: 4.8120. Min Act: -0.1700
Data Index: 6019517 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6558. Min Range: -5.6558
Max Act: 4.8120. Min Act: -0.1700
Data Index: 8775752 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6558. Min Range: -5.6558
Max Act: 4.8120. Min Act: -0.1700
Data Index: 7257492 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6558. Min Range: -5.6558
Max Act: 4.7808. Min Act: -0.1700
Data Index: 2446105 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6558. Min Range: -5.6558
Max Act: 4.7495. Min Act: -0.1700
Data Index: 70196 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6558. Min Range: -5.6558
Max Act: 4.7495. Min Act: -0.1700
Data Index: 5797248 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6558. Min Range: -5.6558
Max Act: 4.7183. Min Act: -0.1700
Data Index: 8503757 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6558. Min Range: -5.6558
Max Act: 4.7183. Min Act: -0.1700
Data Index: 2192541 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6558. Min Range: -5.6558
Max Act: 4.6870. Min Act: -0.1700
Data Index: 542512 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19