Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4004 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5635. Min Range: -7.5635
Max Act: 7.5635. Min Act: -0.1700
Data Index: 6959112 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5635. Min Range: -7.5635
Max Act: 7.1885. Min Act: -0.1700
Data Index: 944266 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5635. Min Range: -7.5635
Max Act: 6.9697. Min Act: -0.1700
Data Index: 8648728 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5635. Min Range: -7.5635
Max Act: 6.6885. Min Act: -0.1700
Data Index: 7480768 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5635. Min Range: -7.5635
Max Act: 6.7197. Min Act: -0.1700
Data Index: 5069490 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5635. Min Range: -7.5635
Max Act: 6.6572. Min Act: -0.1700
Data Index: 7923847 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5635. Min Range: -7.5635
Max Act: 6.6260. Min Act: -0.1700
Data Index: 6905228 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5635. Min Range: -7.5635
Max Act: 6.5947. Min Act: -0.1700
Data Index: 1520999 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5635. Min Range: -7.5635
Max Act: 6.5635. Min Act: -0.1700
Data Index: 8212778 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5635. Min Range: -7.5635
Max Act: 6.5010. Min Act: -0.1700
Data Index: 8013998 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5635. Min Range: -7.5635
Max Act: 6.5010. Min Act: -0.1700
Data Index: 3128826 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5635. Min Range: -7.5635
Max Act: 6.5010. Min Act: -0.1700
Data Index: 8237231 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5635. Min Range: -7.5635
Max Act: 6.5010. Min Act: -0.1700
Data Index: 6938082 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5635. Min Range: -7.5635
Max Act: 6.5010. Min Act: -0.1700
Data Index: 2297220 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5635. Min Range: -7.5635
Max Act: 6.4385. Min Act: -0.1700
Data Index: 8815095 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5635. Min Range: -7.5635
Max Act: 6.4385. Min Act: -0.1700
Data Index: 8237229 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5635. Min Range: -7.5635
Max Act: 6.4385. Min Act: -0.1700
Data Index: 5012717 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5635. Min Range: -7.5635
Max Act: 6.4385. Min Act: -0.1700
Data Index: 5352242 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5635. Min Range: -7.5635
Max Act: 6.4385. Min Act: -0.1700
Data Index: 3547016 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5635. Min Range: -7.5635
Max Act: 6.4385. Min Act: -0.1700
Data Index: 301652 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #19