Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 46 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6110. Min Range: -5.6110
Max Act: 5.6110. Min Act: -0.1700
Data Index: 3777127 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6110. Min Range: -5.6110
Max Act: 5.4860. Min Act: -0.1700
Data Index: 1261686 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6110. Min Range: -5.6110
Max Act: 5.3922. Min Act: -0.1700
Data Index: 8089381 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6110. Min Range: -5.6110
Max Act: 5.3297. Min Act: -0.1700
Data Index: 2755139 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6110. Min Range: -5.6110
Max Act: 5.2672. Min Act: -0.1700
Data Index: 527245 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6110. Min Range: -5.6110
Max Act: 5.2360. Min Act: -0.1700
Data Index: 1559487 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6110. Min Range: -5.6110
Max Act: 5.2360. Min Act: -0.1700
Data Index: 8079769 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6110. Min Range: -5.6110
Max Act: 5.2360. Min Act: -0.1700
Data Index: 3919009 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6110. Min Range: -5.6110
Max Act: 5.1735. Min Act: -0.1700
Data Index: 357582 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6110. Min Range: -5.6110
Max Act: 5.2360. Min Act: -0.1700
Data Index: 51807 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6110. Min Range: -5.6110
Max Act: 5.2047. Min Act: -0.1700
Data Index: 1559488 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6110. Min Range: -5.6110
Max Act: 5.1735. Min Act: -0.1700
Data Index: 5090831 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6110. Min Range: -5.6110
Max Act: 5.1735. Min Act: -0.1700
Data Index: 6000148 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6110. Min Range: -5.6110
Max Act: 5.1110. Min Act: -0.1700
Data Index: 5630689 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6110. Min Range: -5.6110
Max Act: 5.1110. Min Act: -0.1700
Data Index: 1559489 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6110. Min Range: -5.6110
Max Act: 5.1110. Min Act: -0.1700
Data Index: 7745050 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6110. Min Range: -5.6110
Max Act: 5.1110. Min Act: -0.1700
Data Index: 6934072 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6110. Min Range: -5.6110
Max Act: 5.0797. Min Act: -0.1700
Data Index: 1327895 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6110. Min Range: -5.6110
Max Act: 5.0797. Min Act: -0.1700
Data Index: 7939035 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6110. Min Range: -5.6110
Max Act: 5.0485. Min Act: -0.1700
Data Index: 2097891 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #19