Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5115 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7048. Min Range: -7.7048
Max Act: 7.7048. Min Act: -0.1700
Data Index: 4375518 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7048. Min Range: -7.7048
Max Act: 7.1111. Min Act: -0.1700
Data Index: 4337587 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7048. Min Range: -7.7048
Max Act: 7.1111. Min Act: -0.1700
Data Index: 6634071 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7048. Min Range: -7.7048
Max Act: 6.9861. Min Act: -0.1700
Data Index: 158530 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7048. Min Range: -7.7048
Max Act: 6.9548. Min Act: -0.1700
Data Index: 4904073 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7048. Min Range: -7.7048
Max Act: 6.8923. Min Act: -0.1700
Data Index: 6070011 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7048. Min Range: -7.7048
Max Act: 6.8298. Min Act: -0.1700
Data Index: 7535057 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7048. Min Range: -7.7048
Max Act: 6.8298. Min Act: -0.1700
Data Index: 5360867 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7048. Min Range: -7.7048
Max Act: 6.7673. Min Act: -0.1700
Data Index: 5921017 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7048. Min Range: -7.7048
Max Act: 6.7986. Min Act: -0.1700
Data Index: 4162110 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7048. Min Range: -7.7048
Max Act: 6.7986. Min Act: -0.1700
Data Index: 7050156 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7048. Min Range: -7.7048
Max Act: 6.7673. Min Act: -0.1700
Data Index: 4067003 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7048. Min Range: -7.7048
Max Act: 6.7361. Min Act: -0.1700
Data Index: 6614884 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7048. Min Range: -7.7048
Max Act: 6.7673. Min Act: -0.1700
Data Index: 6321685 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7048. Min Range: -7.7048
Max Act: 6.7361. Min Act: -0.1700
Data Index: 6646495 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7048. Min Range: -7.7048
Max Act: 6.7673. Min Act: -0.1700
Data Index: 1566202 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7048. Min Range: -7.7048
Max Act: 6.7048. Min Act: -0.1700
Data Index: 692517 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7048. Min Range: -7.7048
Max Act: 6.7048. Min Act: -0.1700
Data Index: 534799 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7048. Min Range: -7.7048
Max Act: 6.7048. Min Act: -0.1700
Data Index: 3383429 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7048. Min Range: -7.7048
Max Act: 6.6423. Min Act: -0.1700
Data Index: 2458017 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #19