Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3448 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6058. Min Range: -5.6058
Max Act: 5.6058. Min Act: -0.1700
Data Index: 2241539 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6058. Min Range: -5.6058
Max Act: 5.4183. Min Act: -0.1700
Data Index: 6605920 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6058. Min Range: -5.6058
Max Act: 5.2308. Min Act: -0.1700
Data Index: 7011499 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6058. Min Range: -5.6058
Max Act: 5.1995. Min Act: -0.1700
Data Index: 5604929 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6058. Min Range: -5.6058
Max Act: 5.1370. Min Act: -0.1700
Data Index: 4410690 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6058. Min Range: -5.6058
Max Act: 5.1370. Min Act: -0.1700
Data Index: 2449365 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6058. Min Range: -5.6058
Max Act: 5.1058. Min Act: -0.1700
Data Index: 6536242 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6058. Min Range: -5.6058
Max Act: 5.0745. Min Act: -0.1700
Data Index: 8811119 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6058. Min Range: -5.6058
Max Act: 5.0433. Min Act: -0.1700
Data Index: 8149863 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6058. Min Range: -5.6058
Max Act: 5.0433. Min Act: -0.1700
Data Index: 8149862 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6058. Min Range: -5.6058
Max Act: 5.0433. Min Act: -0.1700
Data Index: 8014787 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6058. Min Range: -5.6058
Max Act: 4.9808. Min Act: -0.1700
Data Index: 5075496 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6058. Min Range: -5.6058
Max Act: 5.0120. Min Act: -0.1700
Data Index: 8612039 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6058. Min Range: -5.6058
Max Act: 5.0120. Min Act: -0.1700
Data Index: 8014796 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6058. Min Range: -5.6058
Max Act: 5.0120. Min Act: -0.1700
Data Index: 1003425 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6058. Min Range: -5.6058
Max Act: 5.0120. Min Act: -0.1700
Data Index: 1720873 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6058. Min Range: -5.6058
Max Act: 4.9808. Min Act: -0.1700
Data Index: 2785276 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6058. Min Range: -5.6058
Max Act: 4.9808. Min Act: -0.1700
Data Index: 3124234 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6058. Min Range: -5.6058
Max Act: 4.9808. Min Act: -0.1700
Data Index: 3637351 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6058. Min Range: -5.6058
Max Act: 4.9808. Min Act: -0.1700
Data Index: 4215052 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #19