Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5619 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9088. Min Range: -6.9088
Max Act: 6.9088. Min Act: -0.1700
Data Index: 1805576 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9088. Min Range: -6.9088
Max Act: 6.8150. Min Act: -0.1700
Data Index: 3525180 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9088. Min Range: -6.9088
Max Act: 6.6900. Min Act: -0.1700
Data Index: 134938 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9088. Min Range: -6.9088
Max Act: 6.5025. Min Act: -0.1700
Data Index: 2344692 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9088. Min Range: -6.9088
Max Act: 6.4713. Min Act: -0.1700
Data Index: 2544237 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9088. Min Range: -6.9088
Max Act: 6.4400. Min Act: -0.1700
Data Index: 5323512 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9088. Min Range: -6.9088
Max Act: 6.4400. Min Act: -0.1700
Data Index: 7584593 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9088. Min Range: -6.9088
Max Act: 6.4088. Min Act: -0.1700
Data Index: 5129558 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9088. Min Range: -6.9088
Max Act: 6.4088. Min Act: -0.1700
Data Index: 5265754 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9088. Min Range: -6.9088
Max Act: 6.3463. Min Act: -0.1700
Data Index: 893196 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9088. Min Range: -6.9088
Max Act: 6.3150. Min Act: -0.1700
Data Index: 7145554 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9088. Min Range: -6.9088
Max Act: 6.3463. Min Act: -0.1700
Data Index: 262701 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9088. Min Range: -6.9088
Max Act: 6.3463. Min Act: -0.1700
Data Index: 489788 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9088. Min Range: -6.9088
Max Act: 6.3150. Min Act: -0.1700
Data Index: 5309551 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9088. Min Range: -6.9088
Max Act: 6.3150. Min Act: -0.1700
Data Index: 6220299 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9088. Min Range: -6.9088
Max Act: 6.2838. Min Act: -0.1700
Data Index: 3567320 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9088. Min Range: -6.9088
Max Act: 6.2838. Min Act: -0.1700
Data Index: 6716595 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9088. Min Range: -6.9088
Max Act: 6.2838. Min Act: -0.1700
Data Index: 3121195 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9088. Min Range: -6.9088
Max Act: 6.1900. Min Act: -0.1700
Data Index: 6922440 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9088. Min Range: -6.9088
Max Act: 6.1900. Min Act: -0.1700
Data Index: 1928583 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #19