Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5073 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3485. Min Range: -5.3485
Max Act: 5.3485. Min Act: -0.1700
Data Index: 1437535 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3485. Min Range: -5.3485
Max Act: 5.2860. Min Act: -0.1700
Data Index: 5831228 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3485. Min Range: -5.3485
Max Act: 5.2860. Min Act: -0.1700
Data Index: 4583278 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3485. Min Range: -5.3485
Max Act: 5.2235. Min Act: -0.1700
Data Index: 3937628 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3485. Min Range: -5.3485
Max Act: 5.1610. Min Act: -0.1700
Data Index: 2495165 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3485. Min Range: -5.3485
Max Act: 5.1610. Min Act: -0.1700
Data Index: 523082 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3485. Min Range: -5.3485
Max Act: 5.1298. Min Act: -0.1700
Data Index: 4506376 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3485. Min Range: -5.3485
Max Act: 5.0985. Min Act: -0.1700
Data Index: 1926257 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3485. Min Range: -5.3485
Max Act: 5.0673. Min Act: -0.1700
Data Index: 738931 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3485. Min Range: -5.3485
Max Act: 5.0985. Min Act: -0.1700
Data Index: 7123677 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3485. Min Range: -5.3485
Max Act: 5.0673. Min Act: -0.1700
Data Index: 8021738 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3485. Min Range: -5.3485
Max Act: 5.0360. Min Act: -0.1700
Data Index: 6839743 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3485. Min Range: -5.3485
Max Act: 5.0360. Min Act: -0.1700
Data Index: 1477804 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3485. Min Range: -5.3485
Max Act: 5.0360. Min Act: -0.1700
Data Index: 7500076 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3485. Min Range: -5.3485
Max Act: 4.9735. Min Act: -0.1700
Data Index: 574431 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3485. Min Range: -5.3485
Max Act: 4.9423. Min Act: -0.1700
Data Index: 2573746 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3485. Min Range: -5.3485
Max Act: 4.9735. Min Act: -0.1700
Data Index: 5697176 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3485. Min Range: -5.3485
Max Act: 4.9423. Min Act: -0.1700
Data Index: 1139088 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3485. Min Range: -5.3485
Max Act: 4.9110. Min Act: -0.1700
Data Index: 2422674 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3485. Min Range: -5.3485
Max Act: 4.8798. Min Act: -0.1700
Data Index: 6490149 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #19